Search

Unlike the success of neural architecture search (NAS) in high-level vision tasks, it remains challenging to find computationally efficient and memory-efficient solutions to low-level vision problems such as image restoration through NAS. One of the fundamental barriers to differential NAS-based image restoration is the optimization gap between the super-network and the sub-architectures, causing instability during the searching process. In this paper, we present a novel approach to fill this gap in image denoising application by connecting model-guided design (MoD) with NAS (MoD-NAS). Specifically, we propose to construct a new search space under a model-guided framework and develop more stable and efficient differential search strategies. MoD-NAS employs a highly reusable width search strategy and a densely connected search block to automatically select the operations of each layer as well as network width and depth via gradient descent. During the search process, the proposed MoD-NAS remains stable because of the smoother search space designed under the model-guided framework. Experimental results on several popular datasets show that our MoD-NAS method has achieved at least comparable even better PSNR performance than current state-of-the-art methods with fewer parameters, fewer flops, and less testing time.

Typical image aesthetics assessment (IAA) is modeled for the generic aesthetics perceived by an "average" user. However, such generic aesthetics models neglect the fact that users' aesthetic preferences vary significantly depending on their unique preferences. Therefore, it is essential to tackle the issue for personalized IAA (PIAA). Since PIAA is a typical small sample learning (SSL) problem, existing PIAA models are usually built by fine-tuning the well-established generic IAA (GIAA) models, which are regarded as prior knowledge. Nevertheless, this kind of prior knowledge based on "average aesthetics" fails to incarnate the aesthetic diversity of different people. In order to learn the shared prior knowledge when different people judge aesthetics, that is, learn how people judge image aesthetics, we propose a PIAA method based on meta-learning with bilevel gradient optimization (BLG-PIAA), which is trained using individual aesthetic data directly and generalizes to unknown users quickly. The proposed approach consists of two phases: 1) meta-training and 2) meta-testing. In meta-training, the aesthetics assessment of each user is regarded as a task, and the training set of each task is divided into two sets: 1) support set and 2) query set. Unlike traditional methods that train a GIAA model based on average aesthetics, we train an aesthetic meta-learner model by bilevel gradient updating from the support set to the query set using many users' PIAA tasks. In meta-testing, the aesthetic meta-learner model is fine-tuned using a small amount of aesthetic data of a target user to obtain the PIAA model. The experimental results show that the proposed method outperforms the state-of-the-art PIAA metrics, and the learned prior model of BLG-PIAA can be quickly adapted to unseen PIAA tasks.

Video quality assessment (VQA) task is an ongoing small sample learning problem due to the costly effort required for manual annotation. Since existing VQA datasets are of limited scale, prior research tries to leverage models pre-trained on ImageNet to mitigate this kind of shortage. Nonetheless, these well-trained models targeting on image classification task can be sub-optimal when applied on VQA data from a significantly different domain. In this paper, we make the first attempt to perform self-supervised pre-training for VQA task built upon contrastive learning method, targeting at exploiting the plentiful unlabeled video data to learn feature representation in a simple-yet-effective way. Specifically, we implement this idea by first generating distorted video samples with diverse distortion characteristics and visual contents based on the proposed distortion augmentation strategy. Afterwards, we conduct contrastive learning to capture quality-aware information by maximizing the agreement on feature representations of future frames and their corresponding predictions in the embedding space. In addition, we further introduce distortion prediction task as an additional learning objective to push the model towards discriminating different distortion categories of the input video. Solving these prediction tasks jointly with the contrastive learning not only provides stronger surrogate supervision signals, but also learns the shared knowledge among the prediction tasks. Extensive experiments demonstrate that our approach sets a new state-of-the-art in self-supervised learning for VQA task. Our results also underscore that the learned pre-trained model can significantly benefit the existing learning based VQA models. Source code is available at https://github.com/cpf0079/CSPT.

In this paper, we investigate the problem of hyperspectral (HS) image spatial super-resolution via deep learning. Particularly, we focus on how to embed the high-dimensional spatial-spectral information of HS images efficiently and effectively. Specifically, in contrast to existing methods adopting empirically-designed network modules, we formulate HS embedding as an approximation of the posterior distribution of a set of carefully-defined HS embedding events, including layer-wise spatial-spectral feature extraction and network-level feature aggregation. Then, we incorporate the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable, producing PDE-Net, in which high-resolution (HR) HS images are iteratively refined from the residuals between input low-resolution (LR) HS images and pseudo-LR-HS images degenerated from reconstructed HR-HS images via probability-inspired HS embedding. Extensive experiments over three common benchmark datasets demonstrate that PDE-Net achieves superior performance over state-of-the-art methods. Besides, the probabilistic characteristic of this kind of networks can provide the epistemic uncertainty of the network outputs, which may bring additional benefits when used for other HS image-based applications. The code will be publicly available at https://github.com/jinnh/PDE-Net.

Blind image quality assessment (BIQA), which is capable of precisely and automatically estimating human perceived image quality with no pristine image for comparison, attracts extensive attention and is of wide applications. Recently, many existing BIQA methods commonly represent image quality with a quantitative value, which is inconsistent with human cognition. Generally, human beings are good at perceiving image quality in terms of semantic description rather than quantitative value. Moreover, cognition is a needs-oriented task where humans are able to extract image contents with local to global semantics as they need. The mediocre quality value represents coarse or holistic image quality and fails to reflect degradation on hierarchical semantics. In this paper, to comply with human cognition, a novel quality caption model is inventively proposed to measure fine-grained image quality with hierarchical semantics degradation. Research on human visual system indicates there are hierarchy and reverse hierarchy correlations between hierarchical semantics. Meanwhile, empirical evidence shows that there are also bi-directional degradation dependencies between them. Thus, a novel bi-directional relationship-based network (BDRNet) is proposed for semantics degradation description, through adaptively exploring those correlations and degradation dependencies in a bi-directional manner. Extensive experiments demonstrate that our method outperforms the state-of-the-arts in terms of both evaluation performance and generalization ability.

Blind image quality assessment (BIQA) is a useful but challenging task. It is a promising idea to design BIQA methods by mimicking the working mechanism of human visual system (HVS). The internal generative mechanism (IGM) indicates that the HVS actively infers the primary content (i.e., meaningful information) of an image for better understanding. Inspired by that, this paper presents a novel BIQA metric by mimicking the active inference process of IGM. Firstly, an active inference module based on the generative adversarial network (GAN) is established to predict the primary content, in which the semantic similarity and the structural dissimilarity (i.e., semantic consistency and structural completeness) are both considered during the optimization. Then, the image quality is measured on the basis of its primary content. Generally, the image quality is highly related to three aspects, i.e., the scene information (content-dependency), the distortion type (distortion-dependency), and the content degradation (degradation-dependency). According to the correlation between the distorted image and its primary content, the three aspects are analyzed and calculated respectively with a multi-stream convolutional neural network (CNN) based quality evaluator. As a result, with the help of the primary content obtained from the active inference and the comprehensive quality degradation measurement from the multi-stream CNN, our method achieves competitive performance on five popular IQA databases. Especially in cross-database evaluations, our method achieves significant improvements.

Quality of experience (QoE) that serves as a direct evaluation of viewing experience from the end users is of vital importance for network optimization, and should be constantly monitored. Unlike existing video-on-demand streaming services, real-time interactivity is critical to the mobile live broadcasting experience for both broadcasters and their audiences. While existing QoE metrics that are validated on limited video contents and synthetic stall patterns have shown effectiveness in their trained QoE benchmarks, a common caveat is that they often encounter challenges in practical live broadcasting scenarios, where one needs to accurately understand the activity in the video with fluctuating QoE and figure out what is going to happen to support the real-time feedback to the broadcaster. In this paper, we propose a temporal relational reasoning guided QoE evaluation approach for mobile live video broadcasting, namely TRR-QoE, which explicitly attends to the temporal relationships between consecutive frames to achieve a more comprehensive understanding of the distortion-aware variation. In our design, video frames are first processed by deep neural network (DNN) to extract quality-indicative features. Afterwards, besides explicitly integrating features of individual frames to account for the spatial distortion information, multi-scale temporal relational information corresponding to diverse temporal resolutions are made full use of to capture temporal-distortion-aware variation. As a result, the overall QoE prediction could be derived by combining both aspects. The results of experiments conducted on a number of benchmark databases demonstrate the superiority of TRR-QoE over the representative state-of-the-art metrics.

The trade-off between spatial and spectral resolution is one of the fundamental issues in hyperspectral images (HSI). Given the challenges of directly acquiring high-resolution hyperspectral images (HR-HSI), a compromised solution is to fuse a pair of images: one has high-resolution (HR) in the spatial domain but low-resolution (LR) in spectral-domain and the other vice versa. Model-based image fusion methods including pan-sharpening aim at reconstructing HR-HSI by solving manually designed objective functions. However, such hand-crafted prior often leads to inevitable performance degradation due to a lack of end-to-end optimization. Although several deep learning-based methods have been proposed for hyperspectral pan-sharpening, HR-HSI related domain knowledge has not been fully exploited, leaving room for further improvement. In this paper, we propose an iterative Hyperspectral Image Super-Resolution (HSISR) algorithm based on a deep HSI denoiser to leverage both domain knowledge likelihood and deep image prior. By taking the observation matrix of HSI into account during the end-to-end optimization, we show how to unfold an iterative HSISR algorithm into a novel model-guided deep convolutional network (MoG-DCN). The representation of the observation matrix by subnetworks also allows the unfolded deep HSISR network to work with different HSI situations, which enhances the flexibility of MoG-DCN. Extensive experimental results are reported to demonstrate that the proposed MoG-DCN outperforms several leading HSISR methods in terms of both implementation cost and visual quality. The code is available at https://see.xidian.edu.cn/faculty/wsdong/Projects/MoG-DCN.htm.

View synthesis is a key technique in free-viewpoint video, which renders virtual views based on texture and depth images. The distortions in synthesized views come from two stages, i.e., the stage of the acquisition and processing of texture and depth images, and the rendering stage using depth-image-based-rendering (DIBR) algorithms. The existing view synthesis quality metrics are designed for the distortions caused by a single stage, which cannot accurately evaluate the quality of the entire view synthesis process. With the considerations that the distortions introduced by two stages both cause edge degradation and texture unnaturalness, and the Difference-of-Gaussian (DoG) representation is powerful in capturing image edge and texture characteristics by simulating the center-surrounding receptive fields of retinal ganglion cells of human eyes, this paper presents a no-reference quality index for Synthesized views using DoG-based Edge statistics and Texture naturalness (SET). To mimic the multi-scale property of the Human Visual System (HVS), DoG images are first calculated at multiple scales. Then the orientation selective statistics features and the texture naturalness features are calculated on the DoG images and the coarsest scale image, producing two groups of quality-aware features. Finally, the quality model is learnt from these features using the random forest regression model. Experimental results on two view synthesis image databases demonstrate that the proposed metric is advantageous over the relevant state-of-the-arts in dealing with the distortions in the whole view synthesis process.

Recovering the background and foreground parts from video frames has important applications in video surveillance. Under the assumption that the background parts are stationary and the foreground are sparse, most of existing methods are based on the framework of robust principal component analysis (RPCA), i.e., modeling the background and foreground parts as a low-rank and sparse matrices, respectively. However, in realistic complex scenarios, the conventional norm sparse regularizer often fails to well characterize the varying sparsity of the foreground components. How to select the sparsity regularizer parameters adaptively according to the local statistics is critical to the success of the RPCA framework for background subtraction task. In this paper, we propose to model the sparse component with a Gaussian scale mixture (GSM) model. Compared with the conventional norm, the GSM-based sparse model has the advantages of jointly estimating the variances of the sparse coefficients (and hence the regularization parameters) and the unknown sparse coefficients, leading to significant estimation accuracy improvements. Moreover, considering that the foreground parts are highly structured, a structured extension of the GSM model is further developed. Specifically, the input frame is divided into many homogeneous regions using superpixel segmentation. By characterizing the set of sparse coefficients in each homogeneous region with the same GSM prior, the local dependencies among the sparse coefficients can be effectively exploited, leading to further improvements for background subtraction. Experimental results on several challenging scenarios show that the proposed method performs much better than most of existing background subtraction methods in terms of both performance and speed.

Recovering a high-resolution (HR) image from its low-resolution (LR) version is an ill-posed inverse problem. Learning accurate prior of HR images is of great importance to solve this inverse problem. Existing super-resolution (SR) methods either learn a non-parametric image prior from training data (a large set of LR/HR patch pairs) or estimate a parametric prior from the LR image analytically. Both methods have their limitations: the former lacks flexibility when dealing with different SR settings; while the latter often fails to adapt to spatially varying image structures. In this paper, we propose to take a hybrid approach toward image SR by combining those two lines of ideas - that is, a parametric sparse prior of HR images is learned from the training set as well as the input LR image. By exploiting the strengths of both worlds, we can more accurately recover the sparse codes and therefore HR image patches than conventional sparse coding approaches. Experimental results show that the proposed hybrid SR method significantly outperforms existing model-based SR methods and is highly competitive to current state-of-the-art learning-based SR methods in terms of both subjective and objective image qualities.

In this paper, we propose a novel no reference quality assessment method by incorporating statistical luminance and texture features (NRLT) for screen content images (SCIs) with both local and global feature representation. The proposed method is designed inspired by the perceptual property of the human visual system (HVS) that the HVS is sensitive to luminance change and texture information for image perception. In the proposed method, we first calculate the luminance map through the local normalization, which is further used to extract the statistical luminance features in global scope. Second, inspired by existing studies from neuroscience that high-order derivatives can capture image texture, we adopt four filters with different directions to compute gradient maps from the luminance map. These gradient maps are then used to extract the second-order derivatives by local binary pattern. We further extract the texture feature by the histogram of high-order derivatives in global scope. Finally, support vector regression is applied to train the mapping function from quality-aware features to subjective ratings. Experimental results on the public large-scale SCI database show that the proposed NRLT can achieve better performance in predicting the visual quality of SCIs than relevant existing methods, even including some full reference visual quality assessment methods.

Hyperspectral imaging has many applications from agriculture and astronomy to surveillance and mineralogy. However, it is often challenging to obtain high-resolution (HR) hyperspectral images using existing hyperspectral imaging techniques due to various hardware limitations. In this paper, we propose a new hyperspectral image super-resolution method from a low-resolution (LR) image and a HR reference image of the same scene. The estimation of the HR hyperspectral image is formulated as a joint estimation of the hyperspectral dictionary and the sparse codes based on the prior knowledge of the spatial-spectral sparsity of the hyperspectral image. The hyperspectral dictionary representing prototype reflectance spectra vectors of the scene is first learned from the input LR image. Specifically, an efficient non-negative dictionary learning algorithm using the block-coordinate descent optimization technique is proposed. Then, the sparse codes of the desired HR hyperspectral image with respect to learned hyperspectral basis are estimated from the pair of LR and HR reference images. To improve the accuracy of non-negative sparse coding, a clustering-based structured sparse coding method is proposed to exploit the spatial correlation among the learned sparse codes. The experimental results on both public datasets and real LR hypspectral images suggest that the proposed method substantially outperforms several existing HR hyperspectral image recovery techniques in the literature in terms of both objective quality metrics and computational efficiency.

The human visual system is highly adaptive to extract structure information for scene perception, and structure character is widely used in perception-oriented image processing works. However, the existing structure descriptors mainly describe the luminance contrast of a local region, but cannot effectively represent the spatial correlation of structure. In this paper, we introduce a novel structure descriptor according to the orientation selectivity mechanism in the primary visual cortex. Research on cognitive neuroscience indicate that the arrangement of excitatory and inhibitory cortex cells arise orientation selectivity in a local receptive field, within which the primary visual cortex performs visual information extraction for scene understanding. Inspired by the orientation selectivity mechanism, we compute the correlations among pixels in a local region based on the similarities of their preferred orientation. By imitating the arrangement of the excitatory/inhibitory cells, the correlations between a central pixel and its local neighbors are binarized, and the spatial correlation is represented with a set of binary values, which is named the orientation selectivity-based pattern. Then, taking both the gradient magnitude and the orientation selectivity-based pattern into account, a rotation invariant structure descriptor is introduced. The proposed structure descriptor is applied in texture classification and reduced reference image quality assessment, as two different application domains to verify its generality and robustness. Experimental results demonstrate that the orientation selectivity-based structure descriptor is robust to disturbance, and can effectively represent the structure degradation caused by different types of distortion.

A model of visual masking, which reveals the visibility of stimuli in the human visual system (HVS), is useful in perceptual based image/video processing. The existing visual masking function mainly considers luminance contrast, which always overestimates the visibility threshold of the edge region and underestimates that of the texture region. Recent research on visual perception indicates that the HVS is sensitive to orderly regions that possess regular structures and insensitive to disorderly regions that possess uncertain structures. Therefore, structural uncertainty is another determining factor on visual masking. In this paper, we introduce a novel pattern masking function based on both luminance contrast and structural uncertainty. Through mimicking the internal generative mechanism of the HVS, a prediction model is firstly employed to separate out the unpredictable uncertainty from an input image. In addition, an improved local binary pattern is introduced to compute the structural uncertainty. Finally, combining luminance contrast with structural uncertainty, the pattern masking function is deduced. Experimental result demonstrates that the proposed pattern masking function outperforms the existing visual masking function. Furthermore, we extend the pattern masking function to just noticeable difference (JND) estimation and introduce a novel pixel domain JND model. Subjective viewing test confirms that the proposed JND model is more consistent with the HVS than the existing JND models.

Objective image quality assessment (IQA) aims to evaluate image quality consistently with human perception. Most of the existing perceptual IQA metrics cannot accurately represent the degradations from different types of distortion, e.g., existing structural similarity metrics perform well on content-dependent distortions while not as well as peak signal-to-noise ratio (PSNR) on content-independent distortions. In this paper, we integrate the merits of the existing IQA metrics with the guide of the recently revealed internal generative mechanism (IGM). The IGM indicates that the human visual system actively predicts sensory information and tries to avoid residual uncertainty for image perception and understanding. Inspired by the IGM theory, we adopt an autoregressive prediction algorithm to decompose an input scene into two portions, the predicted portion with the predicted visual content and the disorderly portion with the residual content. Distortions on the predicted portion degrade the primary visual information, and structural similarity procedures are employed to measure its degradation; distortions on the disorderly portion mainly change the uncertain information and the PNSR is employed for it. Finally, according to the noise energy deployment on the two portions, we combine the two evaluation results to acquire the overall quality score. Experimental results on six publicly available databases demonstrate that the proposed metric is comparable with the state-of-the-art quality metrics.