Search

Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually use the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to that of the NLA with randomly selected regions prompted us to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and a pre-trained model were uploaded to GitHub (https://github.com/laoyangui/HSPAN) for validation. [ABSTRACT FROM AUTHOR]

This paper addresses digital staining and classification of the unstained white blood cell images obtained with a differential contrast microscope. We have data coming from multiple domains that are partially labeled and partially matching across the domains. Using unstained images removes time-consuming staining procedures and could facilitate and automatize comprehensive diagnostics. To this aim, we propose a method that translates unstained images to realistically looking stained images preserving the inter-cellular structures, crucial for the medical experts to perform classification. We achieve better structure preservation by adding auxiliary tasks of segmentation and direct reconstruction. Segmentation enforces that the network learns to generate correct nucleus and cytoplasm shape, while direct reconstruction enforces reliable translation between the matching images across domains. Besides, we build a robust domain agnostic latent space by injecting the target domain label directly to the generator, i.e., bypassing the encoder. It allows the encoder to extract features independently of the target domain and enables an automated domain invariant classification of the white blood cells. We validated our method on a large dataset composed of leukocytes of 24 patients, achieving state-of-the-art performance on both digital staining and classification tasks. [ABSTRACT FROM AUTHOR]

The paper proposes a method to effectively fuse multi-exposure inputs and generate high-quality high dynamic range (HDR) images with unpaired datasets. Deep learning-based HDR image generation methods rely heavily on paired datasets. The ground truth images play a leading role in generating reasonable HDR images. Datasets without ground truth are hard to be applied to train deep neural networks. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain $X$ to target domain $Y$ in the absence of paired examples. In this paper, we propose a GAN-based network for solving such problems while generating enjoyable HDR results, named UPHDR-GAN. The proposed method relaxes the constraint of the paired dataset and learns the mapping from the LDR domain to the HDR domain. Although the pair data are missing, UPHDR-GAN can properly handle the ghosting artifacts caused by moving objects or misalignments with the help of the modified GAN loss, the improved discriminator network and the useful initialization phase. The proposed method preserves the details of important regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against the representative methods demonstrate the superiority of the proposed UPHDR-GAN. [ABSTRACT FROM AUTHOR]

In this technical report, we focus on reproducing the results reported in the paper “MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization” [1]. MemXCT is a scalable approach to X-ray Computed Tomography reconstruction which removes redundant computation. We reproduced the single CPU/GPU performance as well as strong scaling experiments. We set up our configurations on Microsoft Azure CycleCloud and have two clusters. One cluster has 4 nodes with 60 CPUs on each node and the other cluster has 4 nodes with 4 NVIDIA V100 GPUs on each node. Both clusters come with InfiniBand. The original author conducted his experiments on Theta and Blue Waters supercomputers. We were able to reproduce part of the results in the original paper, however, failed to produce similar performance on other experiments. This report was submitted as part of the reproducibility challenge in SC20 Student Cluster Competition. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108. [ABSTRACT FROM AUTHOR]

This report analyzes the reproducibility of the paper “MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization” by Hidayetoğlu et al. in the cloud as part of the SC20 Virtual Student Cluster Competition (VSCC). To reproduce the results from the original work, the ETH Zürich SC20 VSCC team performed a series of CT reconstructions and performed a scaling study using three provided sinograms. All experimental runs were performed during the SC20 VSCC on an HPC cluster hosted in the Microsoft Azure CycleCloud. In this paper, we describe discrepancies in results as a factor of the differences in experiment environments and insufficient parameter tuning. We successfully reproduce the single device performance and partially reproduce the strong scaling behavior. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108. [ABSTRACT FROM AUTHOR]

Part information has been proven to be resistant to occlusions and viewpoint changes, which are main difficulties in car parsing and reconstruction. However, in the absence of datasets and approaches incorporating car parts, there are limited works that benefit from it. In this paper, we propose the first part-aware approach for joint part-level car parsing and reconstruction in single street view images. Without labor-intensive part annotations on real images, our approach simultaneously estimates pose, shape, and semantic parts of cars. There are two contributions in this paper. First, our network introduces dense part information to facilitate pose and shape estimation, which is further optimized with a novel 3D loss. To obtain part information in real images, a class-consistent method is introduced to implicitly transfer part knowledge from synthesized images. Second, we construct the first high-quality dataset containing 348 car models with physical dimensions and part annotations. Given these models, 60K synthesized images with randomized configurations are generated. Experimental results demonstrate that part knowledge can be effectively transferred with our class-consistent method, which significantly improves part segmentation performance on real street views. By fusing dense part information, our pose and shape estimation results achieve the state-of-the-art performance on the ApolloCar3D and outperform previous approaches by large margins in terms of both A3DP-Abs and A3DP-Rel. [ABSTRACT FROM AUTHOR]

Scene Representation Networks (SRN) have been proven as a powerful tool for novel view synthesis in recent works. They learn a mapping function from the world coordinates of spatial points to radiance color and the scene’s density using a fully connected network. However, scene texture contains complex high-frequency details in practice that is hard to be memorized by a network with limited parameters, leading to disturbing blurry effects when rendering novel views. In this paper, we propose to learn ‘residual color’ instead of ‘radiance color’ for novel view synthesis, i.e., the residuals between surface color and reference color. Here the reference color is calculated based on spatial color priors, which are extracted from input view observations. The beauty of such a strategy lies in that the residuals between radiance color and reference are close to zero for most spatial points thus are easier to learn. A novel view synthesis system that learns the residual color using SRN is presented in this paper. Experiments on public datasets demonstrate that the proposed method achieves competitive performance in preserving high-resolution details, leading to visually more pleasant results than the state of the arts. [ABSTRACT FROM AUTHOR]

Machine learning models have been shown to be vulnerable to adversarial examples. While most of the existing methods for adversarial attack and defense work on the 2D image domain, a few recent attempts have been made to extend them to 3D point cloud data. However, adversarial results obtained by these methods typically contain point outliers, which are both noticeable and easy to defend against using the simple techniques of outlier removal. Motivated by the different mechanisms by which humans perceive 2D images and 3D shapes, in this paper we propose the new design of geometry-aware objectives, whose solutions favor (the discrete versions of) the desired surface properties of smoothness and fairness. To generate adversarial point clouds, we use a targeted attack misclassification loss that supports continuous pursuit of increasingly malicious signals. Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack ($GeoA^3$ G e o A 3 ). The results of $GeoA^3$ G e o A 3 tend to be more harmful, arguably harder to defend against, and of the key adversarial characterization of being imperceptible to humans. While the main focus of this paper is to learn to generate adversarial point clouds, we also present a simple but effective algorithm termed $Geo_{+}A^3$ G e o + A 3 -IterNormPro, with Iterative Normal Projection (IterNorPro) that solves a new objective function $Geo_{+}A^3$ G e o + A 3 , towards surface-level adversarial attacks via generation of adversarial point clouds. We quantitatively evaluate our methods on both synthetic and physical objects in terms of attack success rate and geometric regularity. For a qualitative evaluation, we conduct subjective studies by collecting human preferences from Amazon Mechanical Turk. Comparative results in comprehensive experiments confirm the advantages of our proposed methods. Our source codes are publicly available at https://github.com/Yuxin-Wen/GeoA3. [ABSTRACT FROM AUTHOR]

Spatial failure patterns in wafer defect maps are very useful for root cause analysis, which is essential for yield optimization in the manufacturing process. Especially, the scratch defect type is the most challenging pattern to recognize because the position, shape, size and curvature vary widely from one scratch to another. Discontinuity points within scratches also contribute to the low recognition rate, and such points are often hidden defective dies that become reliability threat. Previous studies on defect pattern identification show that the recognition rate for scratches is among the lowest in all patterns even if the overall accuracy is high. In this paper, we propose a novel scratch pattern recognition method. In this paper, image processing techniques are applied to recognize scratch patterns in wafer maps. The Hough transform is first employed to identify line segments, from which scratches can be reconstructed. In contrast to previous machine-learning based methods, there is no need to train a complicated prediction model so that the computation time is small. The method is validated by using wafer maps from six real products and public data. Experimental results show that the proposed method achieves high recall, precision and accuracy in all cases. [ABSTRACT FROM AUTHOR]

In this paper, we propose a deep neural network for single image reflection removal. More specifically, we design a convolutional-grid module and take it as the building block of a feature fusion pyramid. The module leverages the combination effect of the grid topology to create a rich ensemble of receptive fields. Embedding the modules into a pyramidal architecture further expands the coverage of receptive fields. Another benefit of the pyramid is to fuse the multi-scale features learned by the modules locating at the ascending and descending pathways. The rich diversity of features helps the neural network analyze the contexts around overlapping objects at various spatial ranges and harvest the cues for layer separation. The proposed work also exploits useful semantic cues from the hyper-column descriptors generated by a pre-trained VGG-19 model to reduce the ambiguity of layer separation. In light of the low correlation between background and reflection layers, we design a channel-correlation based conditional discriminator to penalize residual reflection. The discriminator uses channel-wise attention to screen the features that can distinguish real background images from estimated ones. This paper also presents a task-driven regularization strategy. The high sensitivity of semantic segmentation to reflection is exploited for assessing the completeness of reflection removal. Training with this regularization strategy can boost the performance of both reflection removal and high-level task. The comparison against state-of-the-art algorithms on four public benchmark datasets demonstrates that this work exhibits superior performance in handling the complex reflections in wild scenarios. The proposed network architecture is also applicable to haze removal, which is another ill-posed layer separation problem, and has shown encouraging performance. [ABSTRACT FROM AUTHOR]

Defect detection is a crucial but challenging task in thin film transistor liquid crystal display (TFT-LCD) manufacturing. Existing vision-based methods focus on either spatial domain or frequency domain with unsatisfactory detection. In view of that, this paper proposes a hybrid template matching method by drawing benefits from both frequency and spatial domain techniques. Under proposal, frequency domain template matching method and saliency detector method are firstly adopted separately to obtain two candidate frequency components associated with defects. In template matching process, a novel selection criterion is taken to improve identifying components associated with local spatial anomaly. Subsequently, the inverse Fourier transform is applied on the intersection of the two candidates to reconstruct the defect regions. In final steps, image entropy in the spatial domain is employed to filter out false detection regions to improve accuracy. To meet industry’s real-time inspection requirement, image partition and multi-threading calculation techniques are introduced into the proposed methodology. Experimental results have shown practical viability of the proposed approach to increase the yield rate of panels through robust defect detection in TFT-LCD manufacturing. [ABSTRACT FROM AUTHOR]

Low-rank tensor representation philosophy has enjoyed a reputation in many hyperspectral image (HSI) low-level vision applications, but previous studies often failed to comprehensively exploit the low-rank nature of HSI along different modes in low-dimensional subspace, and unsurprisingly handled only one specific task. To address these challenges, in this paper, we figured out that in addition to the spatial correlation, the spectral dependency of HSI also implicitly exists in the coefficient tensor of its subspace, this crucial dependency that was not fully utilized by previous studies yet can be effectively exploited in a cascaded manner. This led us to propose a unified subspace low-rank learning regime with a new tensor cascaded rank minimization, named STCR, to fully couple the low-rankness of HSI in different domains for various low-level vision tasks. Technically, the high-dimensional HSI was first projected into a low-dimensional tensor subspace, then a novel tensor low-cascaded-rank decomposition was designed to collapse the constructed tensor into three core tensors in succession to more thoroughly exploit the correlations in spatial, nonlocal, and spectral modes of the coefficient tensor. Next, difference continuity-regularization was introduced to learn a basis that more closely approximates the HSI’s endmembers. The proposed regime realizes a comprehensive delineation of the self-portrait of HSI tensor. Extensive evaluations conducted with dozens of state-of-the-art (SOTA) baselines on eight datasets verified that the proposed regime is highly effective and robust to typical HSI low-level vision tasks, including denoising, compressive sensing reconstruction, inpainting, and destriping. The source code of our method is released at https://github.com/CX-He/STCR.git. [ABSTRACT FROM AUTHOR]

Recent learning-based intrinsic image decomposition methods have achieved remarkable progress. However, they usually require massive ground truth intrinsic images for supervised learning, which limits their applicability on real-world images since obtaining ground truth intrinsic decomposition for natural images is very challenging. In this paper, we present an unsupervised framework that is able to learn the decomposition effectively from a single natural image by training solely with the image itself. Our approach is built upon the observations that the reflectance of a natural image typically has high internal self-similarity of patches, and a convolutional generation network tends to boost the self-similarity of an image when trained for image reconstruction. Based on the observations, an unsupervised intrinsic decomposition network (UIDNet) consisting of two fully convolutional encoder-decoder sub-networks, i.e., reflectance prediction network (RPN) and shading prediction network (SPN), is devised to decompose an image into reflectance and shading by promoting the internal self-similarity of the reflectance component, in a way that jointly trains RPN and SPN to reproduce the given image. A novel loss function is also designed to make effective the training for intrinsic decomposition. Experimental results on three benchmark real-world datasets demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Interactive image restoration aims to generate restored images by adjusting a controlling coefficient which determines the restoration level. Previous works are restricted in modulating image with a single coefficient. However, real images always contain multiple types of degradation, which cannot be well determined by one coefficient. To make a step forward, this paper presents a new problem setup, called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels. Compared with the previous single-dimension (SD) modulation, the MD setup to handle multiple degradations adaptively and relief data unbalancing problem in different degradation types. We also propose a deep architecture - CResMD with newly introduced controllable residual connections for multi-dimension modulation. Specifically, we add a controlling variable on the conventional residual connection to allow a weighted summation of input and residual. The values of these weights are generated by another condition network. We further propose a new data sampling strategy based on beta distribution together with a simple loss reweighting approach to balance different degradation types and levels. With corrupted image and degradation information as inputs, the network can output the corresponding restored image. By tweaking the condition vector, users can control the output effects in MD space at test time. Moreover, we also provide an estimation network to predict the condition vector, thus the base network could directly output the restored image without modulation from users. Extensive experiments demonstrate that the proposed CResMD achieves excellent performance on both SD and MD modulation tasks. [ABSTRACT FROM AUTHOR]

This paper reviews the novel concept of a controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offers useful extensions and applications. ControlVAE is a new variational autoencoder (VAE) framework that combines automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value. It leverages a non-linear PI controller, a variant of the proportional-integral-derivative (PID) controller, to dynamically tune the weight of the KL-divergence term in the evidence lower bound (ELBO) using the output KL-divergence as feedback. This allows us to precisely control the KL-divergence to a desired value (set point) that is effective in avoiding posterior collapse and learning disentangled representations. While prior work developed alternative techniques for controlling the KL divergence, we show that our PI controller has better stability properties and thus better convergence, thereby producing better disentangled representations from finite training data. In order to improve the ELBO of ControlVAE over that of the regular VAE, we provide a simplified theoretical analysis to inform the choice of set point for the KL-divergence of ControlVAE. We evaluate the proposed method on three tasks: image generation, language modeling, and disentangled representation learning. The results show that ControlVAE can achieve much better reconstruction quality than the other methods for comparable disentanglement. On the language modeling task, our method can avoid posterior collapse (KL vanishing) and improve the diversity of generated text. Moreover, it can change the optimization trajectory, improving the ELBO and the reconstruction quality for image generation. [ABSTRACT FROM AUTHOR]

Over the last years, with the advent of Generative Adversarial Networks (GANs), many face analysis tasks have accomplished astounding performance, with applications including, but not limited to, face generation and 3D face reconstruction from a single “in-the-wild” image. Nevertheless, to the best of our knowledge, there is no method which can produce render-ready high-resolution 3D faces from “in-the-wild” images and this can be attributed to the: (a) scarcity of available data for training, and (b) lack of robust methodologies that can successfully be applied on very high-resolution data. In this paper, we introduce the first method that is able to reconstruct photorealistic render-ready 3D facial geometry and BRDF from a single “in-the-wild” image. To achieve this, we capture a large dataset of facial shape and reflectance, which we have made public. Moreover, we define a fast and photorealistic differentiable rendering methodology with accurate facial skin diffuse and specular reflection, self-occlusion and subsurface scattering approximation. With this, we train a network that disentangles the facial diffuse and specular reflectance components from a mesh and texture with baked illumination, scanned or reconstructed with a 3DMM fitting method. As we demonstrate in a series of qualitative and quantitative experiments, our method outperforms the existing arts by a significant margin and reconstructs authentic, 4K by 6K-resolution 3D faces from a single low-resolution image, that are ready to be rendered in various applications and bridge the uncanny valley. [ABSTRACT FROM AUTHOR]

Recent learning-based intrinsic image decomposition methods have achieved remarkable progress. However, they usually require massive ground truth intrinsic images for supervised learning, which limits their applicability on real-world images since obtaining ground truth intrinsic decomposition for natural images is very challenging. In this paper, we present an unsupervised framework that is able to learn the decomposition effectively from a single natural image by training solely with the image itself. Our approach is built upon the observations that the reflectance of a natural image typically has high internal self-similarity of patches, and a convolutional generation network tends to boost the self-similarity of an image when trained for image reconstruction. Based on the observations, an unsupervised intrinsic decomposition network (UIDNet) consisting of two fully convolutional encoder-decoder sub-networks, i.e., reflectance prediction network (RPN) and shading prediction network (SPN), is devised to decompose an image into reflectance and shading by promoting the internal self-similarity of the reflectance component, in a way that jointly trains RPN and SPN to reproduce the given image. A novel loss function is also designed to make effective the training for intrinsic decomposition. Experimental results on three benchmark real-world datasets demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Interactive image restoration aims to generate restored images by adjusting a controlling coefficient which determines the restoration level. Previous works are restricted in modulating image with a single coefficient. However, real images always contain multiple types of degradation, which cannot be well determined by one coefficient. To make a step forward, this paper presents a new problem setup, called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels. Compared with the previous single-dimension (SD) modulation, the MD setup to handle multiple degradations adaptively and relief data unbalancing problem in different degradation types. We also propose a deep architecture - CResMD with newly introduced controllable residual connections for multi-dimension modulation. Specifically, we add a controlling variable on the conventional residual connection to allow a weighted summation of input and residual. The values of these weights are generated by another condition network. We further propose a new data sampling strategy based on beta distribution together with a simple loss reweighting approach to balance different degradation types and levels. With corrupted image and degradation information as inputs, the network can output the corresponding restored image. By tweaking the condition vector, users can control the output effects in MD space at test time. Moreover, we also provide an estimation network to predict the condition vector, thus the base network could directly output the restored image without modulation from users. Extensive experiments demonstrate that the proposed CResMD achieves excellent performance on both SD and MD modulation tasks. [ABSTRACT FROM AUTHOR]

This paper reviews the novel concept of a controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offers useful extensions and applications. ControlVAE is a new variational autoencoder (VAE) framework that combines automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value. It leverages a non-linear PI controller, a variant of the proportional-integral-derivative (PID) controller, to dynamically tune the weight of the KL-divergence term in the evidence lower bound (ELBO) using the output KL-divergence as feedback. This allows us to precisely control the KL-divergence to a desired value (set point) that is effective in avoiding posterior collapse and learning disentangled representations. While prior work developed alternative techniques for controlling the KL divergence, we show that our PI controller has better stability properties and thus better convergence, thereby producing better disentangled representations from finite training data. In order to improve the ELBO of ControlVAE over that of the regular VAE, we provide a simplified theoretical analysis to inform the choice of set point for the KL-divergence of ControlVAE. We evaluate the proposed method on three tasks: image generation, language modeling, and disentangled representation learning. The results show that ControlVAE can achieve much better reconstruction quality than the other methods for comparable disentanglement. On the language modeling task, our method can avoid posterior collapse (KL vanishing) and improve the diversity of generated text. Moreover, it can change the optimization trajectory, improving the ELBO and the reconstruction quality for image generation. [ABSTRACT FROM AUTHOR]

Over the last years, with the advent of Generative Adversarial Networks (GANs), many face analysis tasks have accomplished astounding performance, with applications including, but not limited to, face generation and 3D face reconstruction from a single “in-the-wild” image. Nevertheless, to the best of our knowledge, there is no method which can produce render-ready high-resolution 3D faces from “in-the-wild” images and this can be attributed to the: (a) scarcity of available data for training, and (b) lack of robust methodologies that can successfully be applied on very high-resolution data. In this paper, we introduce the first method that is able to reconstruct photorealistic render-ready 3D facial geometry and BRDF from a single “in-the-wild” image. To achieve this, we capture a large dataset of facial shape and reflectance, which we have made public. Moreover, we define a fast and photorealistic differentiable rendering methodology with accurate facial skin diffuse and specular reflection, self-occlusion and subsurface scattering approximation. With this, we train a network that disentangles the facial diffuse and specular reflectance components from a mesh and texture with baked illumination, scanned or reconstructed with a 3DMM fitting method. As we demonstrate in a series of qualitative and quantitative experiments, our method outperforms the existing arts by a significant margin and reconstructs authentic, 4K by 6K-resolution 3D faces from a single low-resolution image, that are ready to be rendered in various applications and bridge the uncanny valley. [ABSTRACT FROM AUTHOR]

State-of-the-art face restoration methods employ deep convolutional neural networks (CNNs) to learn a mapping between degraded and sharp facial patterns by exploring local appearance knowledge. However, most of these methods do not well exploit facial structures and identity information, and only deal with task-specific face restoration (e.g., face super-resolution or deblurring). In this paper, we propose cross-tasks and cross-models plug-and-play 3D facial priors to explicitly embed the network with the sharp facial structures for general face restoration tasks. Our 3D priors are the first to explore 3D morphable knowledge based on the fusion of parametric descriptions of face attributes (e.g., identity, facial expression, texture, illumination, and face pose). Furthermore, the priors can easily be incorporated into any network and are very efficient in improving the performance and accelerating the convergence speed. Firstly, a 3D face rendering branch is set up to obtain 3D priors of salient facial structures and identity knowledge. Secondly, for better exploiting this hierarchical information (i.e., intensity similarity, 3D facial structure, and identity content), a spatial attention module is designed for the image restoration problems. Extensive face restoration experiments including face super-resolution and deblurring demonstrate that the proposed 3D priors achieve superior face restoration results over the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Coronary artery disease (CAD) is a cardiovascular condition with high morbidity and mortality. Intravascular optical coherence tomography (IVOCT) has been considered as an optimal imagining system for the diagnosis and treatment of CAD. Constrained by Nyquist theorem, dense sampling in IVOCT attains high resolving power to delineate cellular structures/features. There is a trade-off between high spatial resolution and fast scanning rate for coronary imaging. In this paper, we propose a viable spectral-spatial acquisition method that down-scales the sampling process in both spectral and spatial domain while maintaining high quality in image reconstruction. The down-scaling schedule boosts data acquisition speed without any hardware modifications. Additionally, we propose a unified multi-scale reconstruction framework, namely Multiscale-Spectral-Spatial-Magnification Network (MSSMN), to resolve highly down-scaled (compressed) OCT images with flexible magnification factors. We incorporate the proposed methods into Spectral Domain OCT (SD-OCT) imaging of human coronary samples with clinical features such as stent and calcified lesions. Our experimental results demonstrate that spectral-spatial down-scaled data can be better reconstructed than data that are down-scaled solely in either spectral or spatial domain. Moreover, we observe better reconstruction performance using MSSMN than using existing reconstruction methods. Our acquisition method and multi-scale reconstruction framework, in combination, may allow faster SD-OCT inspection with high resolution during coronary intervention. [ABSTRACT FROM AUTHOR]

Serial section transmission electron micro-scopy (ssTEM) reveals biological information at a scale of nanometer and plays an important role in the ultrastructural analysis. However, due to the imperfect preparation of biological samples, ssTEM images are usually degraded with various artifacts that greatly challenge the subsequent analysis and visualization. In this paper, we introduce a unified deep learning framework for ssTEM image restoration which addresses three main types of artifacts, i.e., Support Film Folds (SFF), Staining Precipitates (SP), and Missing Sections (MS). To achieve this goal, we first model the appearance of SFF and SP artifacts by conducting comprehensive analyses on the statistics of real degraded images, relying on which we can then simulate a large number of paired images (degraded/artifacts-free) for training a deep restoration network. Then, we design a coarse-to-fine restoration network consisting of three modules, i.e., interpolation, correction, and fusion. The interpolation module exploits the adjacent artifacts-free images for an initial restoration, while the correction module resorts to the degraded image itself to rectify the artifacts. Finally, the fusion module jointly utilizes the above two results to further improve the restoration fidelity. Experimental results on both synthetic and real test data validate the significantly improved performance of our proposed framework over existing solutions, in terms of both image restoration fidelity and neuron segmentation accuracy. To the best of our knowledge, this is the first unified deep learning framework for ssTEM image restoration from different types of artifacts. Code is available at https://github.com/sydeng99/ssTEM-restoration. [ABSTRACT FROM AUTHOR]

The recent success in supervised multi-view stereopsis (MVS) relies on the onerously collected real-world 3D data. While the latest differentiable rendering techniques enable unsupervised MVS, they are restricted to discretized (e.g., point cloud) or implicit geometric representation, suffering from either low integrity for a textureless region or less geometric details for complex scenes. In this paper, we propose SurRF, an unsupervised MVS pipeline by learning Surface Radiance Field, i.e., a radiance field defined on a continuous and explicit 2D surface. Our key insight is that, in a local region, the explicit surface can be gradually deformed from a continuous initialization along view-dependent camera rays by differentiable rendering. That enables us to define the radiance field only on a 2D deformable surface rather than in a dense volume of 3D space, leading to compact representation while maintaining complete shape and realistic texture for large-scale complex scenes. We experimentally demonstrate that the proposed SurRF produces competitive results over the-state-of-the-art on various real-world challenging scenes, without any 3D supervision. Moreover, SurRF shows great potential in owning the joint advantages of mesh (scene manipulation), continuous surface (high geometric resolution), and radiance field (realistic rendering). [ABSTRACT FROM AUTHOR]

Non-Line-of-Sight (NLOS) imaging reconstructs occluded scenes based on indirect diffuse reflections. The computational complexity and memory consumption of existing NLOS reconstruction algorithms make them challenging to be implemented in real-time. This paper presents a fast and memory-efficient phasor field-diffraction-based NLOS reconstruction algorithm. In the proposed algorithm, the radial property of the Rayleigh Sommerfeld diffraction (RSD) kernels along with the linear property of Fourier transform are utilized to reconstruct the Fourier domain representations of RSD kernels using a set of kernel bases. Moreover, memory consumption is further reduced by sampling the kernel bases in a radius direction and constructing them during the run-time. According to the analysis, the memory efficiency can be improved by as much as $\mathbf {220}\times$ 220 × . Experimental results show that compared with the original RSD algorithm, the reconstruction time of the proposed algorithm is significantly reduced with little impact on the final imaging quality. [ABSTRACT FROM AUTHOR]

Motion blur in dynamic scenes is an important yet challenging research topic. Recently, deep learning methods have achieved impressive performance for dynamic scene deblurring. However, the motion information contained in a blurry image has yet to be fully explored and accurately formulated because: (i) the ground truth of dynamic motion is difficult to obtain; (ii) the temporal ordering is destroyed during the exposure; and (iii) the motion estimation from a blurry image is highly ill-posed. By revisiting the principle of camera exposure, motion blur can be described by the relative motions of sharp content with respect to each exposed position. In this paper, we define exposure trajectories, which represent the motion information contained in a blurry image and explain the causes of motion blur. A novel motion offset estimation framework is proposed to model pixel-wise displacements of the latent sharp image at multiple timepoints. Under mild constraints, our method can recover dense, (non-)linear exposure trajectories, which significantly reduce temporal disorder and ill-posed problems. Finally, experiments demonstrate that the recovered exposure trajectories not only capture accurate and interpretable motion information from a blurry image, but also benefit motion-aware image deblurring and warping-based video extraction tasks. Codes are available on https://github.com/yjzhang96/Motion-ETR. [ABSTRACT FROM AUTHOR]

Image demoireing is a multi-faceted image restoration task involving both moire pattern removal and color restoration. In this paper, we raise a general degradation model to describe an image contaminated by moire patterns, and propose a novel multi-scale bandpass convolutional neural network (MBCNN) for single image demoireing. For moire pattern removal, we propose a multi-block-size learnable bandpass filters (M-LBFs), based on a block-wise frequency domain transform, to learn the frequency domain priors of moire patterns. We also introduce a new loss function named Dilated Advanced Sobel loss (D-ASL) to better sense the frequency information. For color restoration, we propose a two-step tone mapping strategy, which first applies a global tone mapping to correct for a global color shift, and then performs local fine tuning of the color per pixel. To determine the most appropriate frequency domain transform, we investigate several transforms including DCT, DFT, DWT, learnable non-linear transform and learnable orthogonal transform. We finally adopt the DCT. Our basic model won the AIM2019 demoireing challenge. Experimental results on three public datasets show that our method outperforms state-of-the-art methods by a large margin. [ABSTRACT FROM AUTHOR]

Structures matter in single image super-resolution (SISR). Benefiting from generative adversarial networks (GANs), recent studies have promoted the development of SISR by recovering photo-realistic images. However, there are still undesired structural distortions in the recovered images. In this paper, we propose a structure-preserving super-resolution (SPSR) method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details. First, we propose SPSR with gradient guidance (SPSR-G) by exploiting gradient maps of images to guide the recovery in two aspects. On the one hand, we restore high-resolution gradient maps by a gradient branch to provide additional structure priors for the SR process. On the other hand, we propose a gradient loss to impose a second-order restriction on the super-resolved images, which helps generative networks concentrate more on geometric structures. Second, since the gradient maps are handcrafted and may only be able to capture limited aspects of structural information, we further extend SPSR-G by introducing a learnable neural structure extractor (NSE) to unearth richer local structures and provide stronger supervision for SR. We propose two self-supervised structure learning methods, contrastive prediction and solving jigsaw puzzles, to train the NSEs. Our methods are model-agnostic, which can be potentially used for off-the-shelf SR networks. Experimental results on five benchmark datasets show that the proposed methods outperform state-of-the-art perceptual-driven SR methods under LPIPS, PSNR, and SSIM metrics. Visual results demonstrate the superiority of our methods in restoring structures while generating natural SR images. Code is available at https://github.com/Maclory/SPSR. [ABSTRACT FROM AUTHOR]

In this paper, we propose an efficient method for robust and accurate 3D self-portraits using a single RGBD camera. Our method can generate detailed and realistic 3D self-portraits in seconds and shows the ability to handle subjects wearing extremely loose clothes. To achieve highly efficient and robust reconstruction, we propose PIFusion, which combines learning-based 3D recovery with volumetric non-rigid fusion to generate accurate sparse partial scans of the subject. Meanwhile, a non-rigid volumetric deformation method is proposed to continuously refine the learned shape prior. Moreover, a lightweight bundle adjustment algorithm is proposed to guarantee that all the partial scans can not only “loop” with each other but also remain consistent with the selected live key observations. Finally, to further generate realistic portraits, we propose non-rigid texture optimization to improve the texture quality. Additionally, we also contribute a benchmark for single-view 3D self-portrait reconstruction, an evaluation dataset that contains 10 single-view RGBD sequences of a self-rotating performer wearing various clothes and the corresponding ground-truth 3D models in the first frame of each sequence. The results and experiments based on this dataset show that the proposed method outperforms state-of-the-art methods on accuracy, efficiency, and generality. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and sparse communication. However, the training of deep SNNs is not straightforward. In this paper, we propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition, which is referred to as progressive tandem learning. By studying the equivalence between ANNs and SNNs in the discrete representation space, a primitive network conversion method is introduced that takes full advantage of spike count to approximate the activation value of ANN neurons. To compensate for the approximation errors arising from the primitive network conversion, we further introduce a layer-wise learning method with an adaptive training scheduler to fine-tune the network weights. The progressive tandem learning framework also allows hardware constraints, such as limited weight precision and fan-in connections, to be progressively imposed during training. The SNNs thus trained have demonstrated remarkable classification and regression capabilities on large-scale object recognition, image reconstruction, and speech separation tasks, while requiring at least an order of magnitude reduced inference time and synaptic operations than other state-of-the-art SNN implementations. It, therefore, opens up a myriad of opportunities for pervasive mobile and embedded devices with a limited power budget. [ABSTRACT FROM AUTHOR]

Many visual and robotics tasks in real-world scenarios rely on robust handling of high speed motion and high dynamic range (HDR) with effectively high spatial resolution and low noise. Such stringent requirements, however, cannot be directly satisfied by a single imager or imaging modality, rather by multi-modal sensors with complementary advantages. In this paper, we address high performance imaging by exploring the synergy between traditional frame-based sensors with high spatial resolution and low sensor noise, and emerging event-based sensors with high speed and high dynamic range. We introduce a novel computational framework, termed Guided Event Filtering (GEF), to process these two streams of input data and output a stream of super-resolved yet noise-reduced events. To generate high quality events, GEF first registers the captured noisy events onto the guidance image plane according to our flow model. it then performs joint image filtering that inherits the mutual structure from both inputs. Lastly, GEF re-distributes the filtered event frame in the space-time volume while preserving the statistical characteristics of the original events. When the guidance images under-perform, GEF incorporates an event self-guiding mechanism that resorts to neighbor events for guidance. We demonstrate the benefits of GEF by applying the output high quality events to existing event-based algorithms across diverse application categories, including high speed object tracking, depth estimation, high frame-rate video synthesis, and super resolution/HDR/color image restoration. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to, the source data. To effectively utilize the source model for adaptation, we propose a novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis). Specifically, SHOT exploits both information maximization and self-supervised learning for the feature extraction module learning to ensure the target features are implicitly aligned with the features of unseen source data via the same hypothesis. Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain. We denote labeling transfer as SHOT++ if the predictions are obtained by SHOT. Extensive experiments on both digit classification and object recognition tasks show that SHOT and SHOT++ achieve results surpassing or comparable to the state-of-the-arts, demonstrating the effectiveness of our approaches for various visual domain adaptation problems. Code will be available at https://github.com/tim-learn/SHOT-plus. [ABSTRACT FROM AUTHOR]

Image quality assessment (IQA) is an important task of image processing and has diverse applications, such as image super-resolution reconstruction, image transmission and monitoring systems. This paper proposes a perceptual hashing algorithm with complementary color wavelet transform (CCWT) and compressed sensing (CS) for reduced-reference (RR) IQA. The CCWT is exploited to decompose input color image into different sub-bands. Since the calculation of CCWT uses all color channels without discarding any information, the distortions introduced by digital operations on color channels are preserved in the CCWT sub-bands. The block-based CS is used to extract features from the CCWT sub-bands. As the Euclidean distance between the block-based CS features is slightly influenced by content-preserving operations, perceptual features constructed by Euclidean distances are robust, discriminative and compact. Hash sequence is finally determined by quantifying the perceptual features. Effectiveness of the proposed hashing is verified by various experiments on four open image databases. Experimental results demonstrate that the proposed hashing is superior to some state-of-the-art algorithms in terms of classification and RR IQA application. [ABSTRACT FROM AUTHOR]

The critical challenge of single image inpainting stems from accurate semantic inference via limited information while maintaining image quality. Typical methods for semantic image inpainting train an encoder-decoder network by learning a one-to-one mapping from the corrupted image to the inpainted version. While such methods perform well on images with small corrupted regions, it is challenging for these methods to deal with images with large corrupted area due to two potential limitations. 1) Such one-to-one mapping paradigm tends to overfit each single training pair of images; 2) The inter-image prior knowledge about the general distribution patterns of visual semantics, which can be transferred across images sharing similar semantics, is not explicitly exploited. In this paper, we propose the Generative Memory-guided Semantic Reasoning Model (GM-SRM), which infers the content of corrupted regions based on not only the known regions of the corrupted image, but also the learned inter-image reasoning priors characterizing the generalizable semantic distribution patterns between similar images. In particular, the proposed GM-SRM first pre-learns a generative memory from the whole training data to explicitly learn the distribution of different semantic patterns. Then the learned memory are leveraged to retrieve the matching semantics for the current corrupted image to perform semantic reasoning during image inpainting. While the encoder-decoder network is used for guaranteeing the pixel-level content consistency, our generative priors are favorable for performing high-level semantic reasoning, which is particularly effective for inferring semantic content for large corrupted area. Extensive experiments on Paris Street View, CelebA-HQ, and Places2 benchmarks demonstrate that our GM-SRM outperforms the state-of-the-art methods for image inpainting in terms of both visual quality and quantitative metrics. [ABSTRACT FROM AUTHOR]

Invertible color-to-grayscale conversion is a research issue in grayscale image colorization, which is a complex problem resulting from information loss. This paper presents an innovative invertible color-to-grayscale conversion idea by independently compressing the chromaticity plane and hiding it into the corresponding luminance plane as a watermark. Since the chromaticity and luminance planes are orthogonal in the proposed method, they can be processed efficiently without mutual influence. By using an efficient lossy compression operation, we can save more chromatic information. By using two high-capacity data hiding techniques (reversible watermarking (RW) and least significant bit (LSB) substitution), we can embed the compressed chromatic information into the luminance plane perfectly. For the purpose of integrality authentication, the luminance plane is hashed as part of the embedded information before the embedding. Experimental results have shown that higher quality of reconstructed color images can be achieved by using RW, but the quality of the synthesized grayscale drops sharply. By using LSB substitution, we can obtain high-quality synthesized grayscale and reconstructed color images simultaneously. Furthermore, we have compared the proposed LSB-based scheme with several recently reported state-of-the-art methods to validate the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

Tensor fields are useful for modeling the structure of biological tissues. The challenge to measure tensor fields involves acquiring sufficient data of scalar measurements that are physically achievable and reconstructing tensors from as few projections as possible for efficient applications in medical imaging. In this paper, we present a filtered back-projection algorithm for the reconstruction of a symmetric second-rank tensor field from directional X-ray projections about three axes. The tensor field is decomposed into a solenoidal and irrotational component, each of three unknowns. Using the Fourier projection theorem, a filtered back-projection algorithm is derived to reconstruct the solenoidal and irrotational components from projections acquired around three axes. A simple illustrative phantom consisting of two spherical shells and a 3D digital cardiac diffusion image obtained from diffusion tensor MRI of an excised human heart are used to simulate directional X-ray projections. The simulations validate the mathematical derivations and demonstrate reasonable noise properties of the algorithm. The decomposition of the tensor field into solenoidal and irrotational components provides insight into the development of algorithms for reconstructing tensor fields with sufficient samples in terms of the type of directional projections and the necessary orbits for the acquisition of the projections of the tensor field. [ABSTRACT FROM AUTHOR]

Image reconstruction for positron emission tomography (PET) is challenging because of the ill-conditioned tomographic problem and low counting statistics. Kernel methods address this challenge by using kernel representation to incorporate image prior information in the forward model of iterative PET image reconstruction. Existing kernel methods construct the kernels commonly using an empirical process, which may lead to unsatisfactory performance. In this paper, we describe the equivalence between the kernel representation and a trainable neural network model. A deep kernel method is then proposed by exploiting a deep neural network to enable automated learning of an improved kernel model and is directly applicable to single subjects in dynamic PET. The training process utilizes available image prior data to form a set of robust kernels in an optimized way rather than empirically. The results from computer simulations and a real patient dataset demonstrate that the proposed deep kernel method can outperform the existing kernel method and neural network method for dynamic PET image reconstruction. [ABSTRACT FROM AUTHOR]

Image classification needs to consider the existence of image degradations in practice. Although degraded images have various levels of degradation, the degradation levels are usually unknown. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The proposed network can automatically infer ensemble weights by using estimated degradation levels of degraded images and features of restored images, where the degradation levels are estimated internally. The proposed network is mainly discussed with JPEG distortion, while degradations of both Gaussian noise and blurring are also examined. We demonstrate that the proposed network can classify degraded images over various levels of degradation. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images. [ABSTRACT FROM AUTHOR]

This paper presents a new method for selecting a patient specific forward model to compensate for anatomical variations in electrical impedance tomography (EIT) monitoring of neonates. The method uses a combination of shape sensors and absolute reconstruction. It takes advantage of a probabilistic approach which automatically selects the best estimated forward model fit from pre-stored library models. Absolute/static image reconstruction is performed as the core of the posterior probability calculations. The validity and reliability of the algorithm in detecting a suitable model in the presence of measurement noise is studied with simulated and measured data from 11 patients. The paper also demonstrates the potential improvements on the clinical parameters extracted from EIT images by considering a unique case study with a neonate patient undergoing computed tomography imaging as clinical indication prior to EIT monitoring. Two well-known image reconstruction techniques, namely GREIT and tSVD, are implemented to create the final tidal images. The impacts of appropriate model selection on the clinical extracted parameters such as center of ventilation and silent spaces are investigated. The results show significant improvements to the final reconstructed images and more importantly to the clinical EIT parameters extracted from the images that are crucial for decision-making and further interventions. [ABSTRACT FROM AUTHOR]

The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. The codes can be found at https://github.com/Jianningli/tmi. [ABSTRACT FROM AUTHOR]

Face hallucination or super-resolution is a practical application of general image super-resolution which has been recently studied by many researchers. The challenge of good face hallucination comes from a variety of poses, illuminations, facial expressions, and other degradations. In many proposed methods, researchers resolve it by using a generative neural network to reduce the perceptual loss so we can generate a photo-realistic image. The problem is that researchers usually overlook the fidelity of the super-resolved image which could affect further facial image processing. Meanwhile, many CNN based approaches cascade multiple networks to extract facial prior information to improve super-resolution quality. Because of the end-to-end design, the details are missing for investigation. In this paper, we combine new techniques in convolutional neural network and random forests to a Hierarchical CNN based Random Forests (HCRF) approach for face super-resolution in a coarse-to-fine manner. In the proposed approach, we focus on a general approach that can handle facial images with various conditions without pre-processing. To the best of our knowledge, this is the first paper that combines the advantages of deep learning with random forests for face super-resolution. To achieve superior performance, we propose two novel CNN models for coarse facial image super-resolution and segmentation and then apply new random forests to target on local facial features refinement making use of the segmentation results. Extensive benchmark experiments on subjective and objective evaluation show that HCRF can achieve comparable speed and competitive performance compared with state-of-the-art super-resolution approaches for very low-resolution images. [ABSTRACT FROM AUTHOR]

Wavelet denoising is a classical and effective approach for reducing noise in images and signals. Suggested in 1994, this approach is carried out by rectifying the coefficients of a noisy image, in the transform domain, using a set of shrinkage functions (SFs). A plethora of papers deals with the optimal shape of the SFs and the transform used. For example, it is widely known that applying SFs in a redundant basis improves the results. However, it is barely known that the shape of the SFs should be changed when the transform used is redundant. In this paper, we introduce a complete picture of the interrelations between the transform used, the optimal shrinkage functions, and the domains in which they are optimized. We suggest three schemes for optimizing the SFs and provide bounds of the remaining noise, in each scheme, with respect to the other alternatives. In particular, we show that for subband optimization, where each SF is optimized independently for a particular band, optimizing the SFs in the spatial domain is always better than or equal to optimizing the SFs in the transform domain. Furthermore, for redundant bases, we provide the expected denoising gain that can be achieved, relative to the unitary basis, as a function of the redundancy rate. [ABSTRACT FROM AUTHOR]

The non-negative matrix factorization (NMF) algorithm represents the original image as a linear combination of a set of basis images. This image representation method is in line with the idea of “parts constitute a whole” in human thinking. The existing deep NMF performs deep factorization on the coefficient matrix. In these methods, the basis images used to represent the original image is essentially obtained by factorizing the original images once. To extract features reflecting the deep localization characteristics of images, a novel deep NMF architecture based on underlying basis images learning is proposed for the first time. The architecture learns the underlying basis images by deep factorization on the basis images matrix. The deep factorization architecture proposed in this paper has strong interpretability. To implement this architecture, this paper proposes a deep non-negative basis matrix factorization algorithm to obtain the underlying basis images. Then, the objective function is established with an added regularization term, which directly constrains the basis images matrix to obtain the basis images with good local characteristics, and a regularized deep non-negative basis matrix factorization algorithm is proposed. The regularized deep nonlinear non-negative basis matrix factorization algorithm is also proposed to handle pattern recognition tasks with complex data. This paper also theoretically proves the convergence of the algorithm. Finally, the experimental results show that the deep NMF architecture based on the underlying basis images learning proposed in this paper can obtain better recognition performance than the other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of reconstructing 3D poses of multiple people from a few calibrated camera views. The main challenge of this problem is to find the cross-view correspondences among noisy and incomplete 2D pose predictions. Most previous methods address this challenge by directly reasoning in 3D using a pictorial structure model, which is inefficient due to the huge state space. We propose a fast and robust approach to solve this problem. Our key idea is to use a multi-way matching algorithm to cluster the detected 2D poses in all views. Each resulting cluster encodes 2D poses of the same person across different views and consistent correspondences across the keypoints, from which the 3D pose of each person can be effectively inferred. The proposed convex optimization based multi-way matching algorithm is efficient and robust against missing and false detections, without knowing the number of people in the scene. Moreover, we propose to combine geometric and appearance cues for cross-view matching. Finally, an efficient tracking method is proposed to track the detected 3D poses across the multi-view video. The proposed approach achieves the state-of-the-art performance on the Campus and Shelf datasets, while being efficient for real-time applications. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive underwater visual reconstruction paradigm that comprises three procedures, i.e., the E-procedure, the R-procedure, and the H-procedure. The E-procedure $enhance$ e n h a n c e s original underwater images based on color compensation balance and weighted image fusion, yielding restored color, sharpened edges, and global contrast. The R-procedure $register$ r e g i s t e r s multiple enhanced underwater images by exploiting global similarity and local deformation. The H-procedure $homogenize$ h o m o g e n i z e s the registered underwater images by multi-scale composition strategy, which eliminates the inhomogeneous transition and brightness difference across overlapping regions, resulting in a reconstructed wide-field underwater image with comfortable and natural visibility. The three procedures operate in a cascade where the former procedure processes underwater images in a way that facilitates the latter one. We refer to the overall three procedures as the Enhancement-Registration-Homogenization (ERH) paradigm. Comprehensive qualitative and quantitative empirical evaluations reveal that our ERH paradigm outperforms state-of-the-art visual reconstruction methods, including the AutoStitch, APAP, SPHP, APNAP, and REW. [ABSTRACT FROM AUTHOR]

This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existing methods achieve varying degrees of success by using different surface representations. However, they all have their own drawbacks, and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topological structures in their learning frameworks. To this end, we propose to learn and use the topology-preserved, skeletal shape representation to assist the downstream task of object surface reconstruction from RGB images. Technically, we propose the novel SkeletonNet design that learns a volumetric representation of a skeleton via a bridged learning of a skeletal point set, where we use parallel decoders each responsible for the learning of points on 1D skeletal curves and 2D skeletal sheets, as well as an efficient module of globally guided subvolume synthesis for a refined, high-resolution skeletal volume; we present a differentiable Point2Voxel layer to make SkeletonNet end-to-end and trainable. With the learned skeletal volumes, we propose two models, the Skeleton-Based Graph Convolutional Neural Network (SkeGCNN) and the Skeleton-Regularized Deep Implicit Surface Network (SkeDISN), which respectively build upon and improve over the existing frameworks of explicit mesh deformation and implicit field learning for the downstream surface reconstruction task. We conduct thorough experiments that verify the efficacy of our proposed SkeletonNet. SkeGCNN and SkeDISN outperform existing methods as well, and they have their own merits when measured by different metrics. Additional results in generalized task settings further demonstrate the usefulness of our proposed methods. We have made our implementation code publicly available at https://github.com/tangjiapeng/SkeletonNet. [ABSTRACT FROM AUTHOR]

Accurate and automatic segmentation of three-dimensional (3D) individual teeth from cone-beam computerized tomography (CBCT) images is a challenging problem because of the difficulty in separating an individual tooth from adjacent teeth and its surrounding alveolar bone. Thus, this paper proposes a fully automated method of identifying and segmenting 3D individual teeth from dental CBCT images. The proposed method addresses the aforementioned difficulty by developing a deep learning-based hierarchical multi-step model. First, it automatically generates upper and lower jaws panoramic images to overcome the computational complexity caused by high-dimensional data and the curse of dimensionality associated with limited training dataset. The obtained 2D panoramic images are then used to identify 2D individual teeth and capture loose- and tight- regions of interest (ROIs) of 3D individual teeth. Finally, accurate 3D individual tooth segmentation is achieved using both loose and tight ROIs. Experimental results showed that the proposed method achieved an F1-score of 93.35 percent for tooth identification and a Dice similarity coefficient of 94.79 percent for individual 3D tooth segmentation. The results demonstrate that the proposed method provides an effective clinical and practical framework for digital dentistry. [ABSTRACT FROM AUTHOR]

Text is a new way to guide human image manipulation. Albeit natural and flexible, text usually suffers from inaccuracy in spatial description, ambiguity in the description of appearance, and incompleteness. We in this paper address these issues. To overcome inaccuracy, we use structured information (e.g., poses) to help identify correct location to manipulate, by disentangling the control of appearance and spatial structure. Moreover, we learn the image-text shared space with derived disentanglement to improve accuracy and quality of manipulation, by separating relevant and irrelevant editing directions for the textual instructions in this space. Our model generates a series of manipulation results by moving source images in this space with different degrees of editing strength. Thus, to reduce the ambiguity in text, our model generates sequential output for manual selection. In addition, we propose an efficient pseudo-label loss to enhance editing performance when the text is incomplete. We evaluate our method on various datasets and show its precision and interactiveness to manipulate human images. [ABSTRACT FROM AUTHOR]