Search

Visual object tracking and segmentation in omnidirectional videos are challenging due to the wide field-of-view and large spherical distortion brought by 360{\deg} images. To alleviate these problems, we introduce a novel representation, extended bounding field-of-view (eBFoV), for target localization and use it as the foundation of a general 360 tracking framework which is applicable for both omnidirectional visual object tracking and segmentation tasks. Building upon our previous work on omnidirectional visual object tracking (360VOT), we propose a comprehensive dataset and benchmark that incorporates a new component called omnidirectional video object segmentation (360VOS). The 360VOS dataset includes 290 sequences accompanied by dense pixel-wise masks and covers a broader range of target categories. To support both the development and evaluation of algorithms in this domain, we divide the dataset into a training subset with 170 sequences and a testing subset with 120 sequences. Furthermore, we tailor evaluation metrics for both omnidirectional tracking and segmentation to ensure rigorous assessment. Through extensive experiments, we benchmark state-of-the-art approaches and demonstrate the effectiveness of our proposed 360 tracking framework and training dataset. Homepage: https://360vots.hkustvgd.com/

Creating large-scale virtual urban scenes with variant styles is inherently challenging. To facilitate prototypes of virtual production and bypass the need for complex materials and lighting setups, we introduce the first vision-and-text-driven texture stylization system for large-scale urban scenes, StyleCity. Taking an image and text as references, StyleCity stylizes a 3D textured mesh of a large-scale urban scene in a semantics-aware fashion and generates a harmonic omnidirectional sky background. To achieve that, we propose to stylize a neural texture field by transferring 2D vision-and-text priors to 3D globally and locally. During 3D stylization, we progressively scale the planned training views of the input 3D scene at different levels in order to preserve high-quality scene content. We then optimize the scene style globally by adapting the scale of the style image with the scale of the training views. Moreover, we enhance local semantics consistency by the semantics-aware style loss which is crucial for photo-realistic stylization. Besides texture stylization, we further adopt a generative diffusion model to synthesize a style-consistent omnidirectional sky image, which offers a more immersive atmosphere and assists the semantic stylization process. The stylized neural texture field can be baked into an arbitrary-resolution texture, enabling seamless integration into conventional rendering pipelines and significantly easing the virtual production prototyping process. Extensive experiments demonstrate our stylized scenes' superiority in qualitative and quantitative performance and user preferences., Comment: Accepted by ECCV2024. Project page: https://chenyingshu.github.io/stylecity3d/

Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. Existing methods have relied mostly on visual features to generate the segmentation masks while treating text features as supporting components. This over-reliance on visual features can lead to suboptimal results, especially in complex scenarios where text prompts are ambiguous or context-dependent. To overcome these challenges, we present a novel framework VATEX to improve referring image segmentation by enhancing object and context understanding with Vision-Aware Text Feature. Our method involves using CLIP to derive a CLIP Prior that integrates an object-centric visual heatmap with text description, which can be used as the initial query in DETR-based architecture for the segmentation task. Furthermore, by observing that there are multiple ways to describe an instance in an image, we enforce feature similarity between text variations referring to the same visual input by two components: a novel Contextual Multimodal Decoder that turns text embeddings into vision-aware text features, and a Meaning Consistency Constraint to ensure further the coherent and consistent interpretation of language expressions with the context understanding obtained from the image. Our method achieves a significant performance improvement on three benchmark datasets RefCOCO, RefCOCO+ and G-Ref. Code is available at: https://nero1342.github.io/VATEX\_RIS., Comment: 30 pages including supplementary

Photorealistic reconstruction relying on 3D Gaussian Splatting has shown promising potential in various domains. However, the current 3D Gaussian Splatting system only supports radiance field reconstruction using undistorted perspective images. In this paper, we present OmniGS, a novel omnidirectional Gaussian splatting system, to take advantage of omnidirectional images for fast radiance field reconstruction. Specifically, we conduct a theoretical analysis of spherical camera model derivatives in 3D Gaussian Splatting. According to the derivatives, we then implement a new GPU-accelerated omnidirectional rasterizer that directly splats 3D Gaussians onto the equirectangular screen space for omnidirectional image rendering. We realize differentiable optimization of the omnidirectional radiance field without the requirement of cube-map rectification or tangent-plane approximation. Extensive experiments conducted in egocentric and roaming scenarios demonstrate that our method achieves state-of-the-art reconstruction quality and high rendering speed using omnidirectional images. The code will be publicly available., Comment: 8 pages, 6 figures

Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video data, attention maps may not well align with the objects of interest across video frames, causing accumulated errors in long-term video processing. In addition, existing techniques have utilised complex architectures, requiring highly computational complexity and hence limiting the ability to integrate video object segmentation into low-powered devices. To address these issues, we propose a new method for self-supervised video object segmentation based on distillation learning of deformable attention. Specifically, we devise a lightweight architecture for video object segmentation that is effectively adapted to temporal changes. This is enabled by deformable attention mechanism, where the keys and values capturing the memory of a video sequence in the attention module have flexible locations updated across frames. The learnt object representations are thus adaptive to both the spatial and temporal dimensions. We train the proposed architecture in a self-supervised fashion through a new knowledge distillation paradigm where deformable attention maps are integrated into the distillation loss. We qualitatively and quantitatively evaluate our method and compare it with existing methods on benchmark datasets including DAVIS 2016/2017 and YouTube-VOS 2018/2019. Experimental results verify the superiority of our method via its achieved state-of-the-art performance and optimal memory usage., Comment: under review

Large language models (LLMs) have demonstrated a powerful ability to answer various queries as a general-purpose assistant. The continuous multi-modal large language models (MLLM) empower LLMs with the ability to perceive visual signals. The launch of GPT-4 (Generative Pre-trained Transformers) has generated significant interest in the research communities. GPT-4V(ison) has demonstrated significant power in both academia and industry fields, as a focal point in a new artificial intelligence generation. Though significant success was achieved by GPT-4V, exploring MLLMs in domain-specific analysis (e.g., marine analysis) that required domain-specific knowledge and expertise has gained less attention. In this study, we carry out the preliminary and comprehensive case study of utilizing GPT-4V for marine analysis. This report conducts a systematic evaluation of existing GPT-4V, assessing the performance of GPT-4V on marine research and also setting a new standard for future developments in MLLMs. The experimental results of GPT-4V show that the responses generated by GPT-4V are still far away from satisfying the domain-specific requirements of the marine professions. All images and prompts used in this study will be available at https://github.com/hkust-vgd/Marine_GPT-4V_Eval, Comment: 51 pages, 36 figures, Repository: https://github.com/hkust-vgd/Marine_GPT-4V_Eval

Text-to-image diffusion techniques have shown exceptional capability of producing high-quality images from text descriptions. This indicates that there exists a strong correlation between the visual and textual domains. In addition, text-image discriminative models such as CLIP excel in image labelling from text prompts, thanks to the rich and diverse information available from open concepts. In this paper, we leverage these technical advances to solve a challenging problem in computer vision: camouflaged instance segmentation. Specifically, we propose a method built upon a state-of-the-art diffusion model, empowered by open-vocabulary to learn multi-scale textual-visual features for camouflaged object representations. Such cross-domain representations are desirable in segmenting camouflaged objects where visual cues are subtle to distinguish the objects from the background, especially in segmenting novel objects which are not seen in training. We also develop technically supportive components to effectively fuse cross-domain features and engage relevant features towards respective foreground objects. We validate our method and compare it with existing ones on several benchmark datasets of camouflaged instance segmentation and generic open-vocabulary instance segmentation. Experimental results confirm the advances of our method over existing ones. We will publish our code and pre-trained models to support future research., Comment: This work is under review

Modern artificial intelligence offers a novel and transformative approach to creating digital art across diverse styles and modalities like images, videos and 3D data, unleashing the power of creativity and revolutionizing the way that we perceive and interact with visual content. This paper reports on recent advances in stylized 3D asset creation and manipulation with the expressive power of neural networks. We establish a taxonomy for neural stylization, considering crucial design choices such as scene representation, guidance data, optimization strategies, and output styles. Building on such taxonomy, our survey first revisits the background of neural stylization on 2D images, and then presents in-depth discussions on recent neural stylization methods for 3D data, accompanied by a mini-benchmark evaluating selected neural field stylization methods. Based on the insights gained from the survey, we highlight the practical significance, open challenges, future research, and potential impacts of neural stylization, which facilitates researchers and practitioners to navigate the rapidly evolving landscape of 3D content creation using modern artificial intelligence.

Portable 360$^\circ$ cameras are becoming a cheap and efficient tool to establish large visual databases. By capturing omnidirectional views of a scene, these cameras could expedite building environment models that are essential for visual localization. However, such an advantage is often overlooked due to the lack of valuable datasets. This paper introduces a new benchmark dataset, 360Loc, composed of 360$^\circ$ images with ground truth poses for visual localization. We present a practical implementation of 360$^\circ$ mapping combining 360$^\circ$ images with lidar data to generate the ground truth 6DoF poses. 360Loc is the first dataset and benchmark that explores the challenge of cross-device visual positioning, involving 360$^\circ$ reference frames, and query frames from pinhole, ultra-wide FoV fisheye, and 360$^\circ$ cameras. We propose a virtual camera approach to generate lower-FoV query frames from 360$^\circ$ images, which ensures a fair comparison of performance among different query types in visual localization tasks. We also extend this virtual camera approach to feature matching-based and pose regression-based methods to alleviate the performance loss caused by the cross-device domain gap, and evaluate its effectiveness against state-of-the-art baselines. We demonstrate that omnidirectional visual localization is more robust in challenging large-scale scenes with symmetries and repetitive structures. These results provide new insights into 360-camera mapping and omnidirectional visual localization with cross-device queries., Comment: CVPR 2024. Project Page: https://huajianup.github.io/research/360Loc/

The integration of neural rendering and the SLAM system recently showed promising results in joint localization and photorealistic view reconstruction. However, existing methods, fully relying on implicit representations, are so resource-hungry that they cannot run on portable devices, which deviates from the original intention of SLAM. In this paper, we present Photo-SLAM, a novel SLAM framework with a hyper primitives map. Specifically, we simultaneously exploit explicit geometric features for localization and learn implicit photometric features to represent the texture information of the observed environment. In addition to actively densifying hyper primitives based on geometric features, we further introduce a Gaussian-Pyramid-based training method to progressively learn multi-level features, enhancing photorealistic mapping performance. The extensive experiments with monocular, stereo, and RGB-D datasets prove that our proposed system Photo-SLAM significantly outperforms current state-of-the-art SLAM systems for online photorealistic mapping, e.g., PSNR is 30% higher and rendering speed is hundreds of times faster in the Replica dataset. Moreover, the Photo-SLAM can run at real-time speed using an embedded platform such as Jetson AGX Orin, showing the potential of robotics applications., Comment: CVPR 2024. Code: https://github.com/HuajianUP/Photo-SLAM - Project Page: https://huajianup.github.io/research/Photo-SLAM/

Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the performance of the downstream tasks drops significantly. This work explores test-time augmentation (TTA) for 3D point clouds. We are inspired by the recent revolution of learning implicit representation and point cloud upsampling, which can produce high-quality 3D surface reconstruction and proximity-to-surface, respectively. Our idea is to leverage the implicit field reconstruction or point cloud upsampling techniques as a systematic way to augment point cloud data. Mainly, we test both strategies by sampling points from the reconstructed results and using the sampled point cloud as test-time augmented data. We show that both strategies are effective in improving accuracy. We observed that point cloud upsampling for test-time augmentation can lead to more significant performance improvement on downstream tasks such as object classification and segmentation on the ModelNet40, ShapeNet, ScanObjectNN, and SemanticKITTI datasets, especially for sparse point clouds., Comment: This paper is accepted in 3DV 2024

Large language models (LLMs), such as ChatGPT/GPT-4, have proven to be powerful tools in promoting the user experience as an AI assistant. The continuous works are proposing multi-modal large language models (MLLM), empowering LLMs with the ability to sense multiple modality inputs through constructing a joint semantic space (e.g. visual-text space). Though significant success was achieved in LLMs and MLLMs, exploring LLMs and MLLMs in domain-specific applications that required domain-specific knowledge and expertise has been less conducted, especially for \textbf{marine domain}. Different from general-purpose MLLMs, the marine-specific MLLM is required to yield much more \textbf{sensitive}, \textbf{informative}, and \textbf{scientific} responses. In this work, we demonstrate that the existing MLLMs optimized on huge amounts of readily available general-purpose training data show a minimal ability to understand domain-specific intents and then generate informative and satisfactory responses. To address these issues, we propose \textbf{MarineGPT}, the first vision-language model specially designed for the marine domain, unlocking the secrets of the ocean to the public. We present our \textbf{Marine-5M} dataset with more than 5 million marine image-text pairs to inject domain-specific marine knowledge into our model and achieve better marine vision and language alignment. Our MarineGPT not only pushes the boundaries of marine understanding to the general public but also offers a standard protocol for adapting a general-purpose assistant to downstream domain-specific experts. We pave the way for a wide range of marine applications while setting valuable data and pre-trained models for future research in both academic and industrial communities., Comment: work in progress. Code and data will be available at https://github.com/hkust-vgd/MarineGPT

Coral reefs formulate the most valuable and productive marine ecosystems, providing habitat for many marine species. Coral reef surveying and analysis are currently confined to coral experts who invest substantial effort in generating comprehensive and dependable reports (\emph{e.g.}, coral coverage, population, spatial distribution, \textit{etc}), from the collected survey data. However, performing dense coral analysis based on manual efforts is significantly time-consuming, the existing coral analysis algorithms compromise and opt for performing down-sampling and only conducting sparse point-based coral analysis within selected frames. However, such down-sampling will \textbf{inevitable} introduce the estimation bias or even lead to wrong results. To address this issue, we propose to perform \textbf{dense coral video segmentation}, with no down-sampling involved. Through video object segmentation, we could generate more \textit{reliable} and \textit{in-depth} coral analysis than the existing coral reef analysis algorithms. To boost such dense coral analysis, we propose a large-scale coral video segmentation dataset: \textbf{CoralVOS} as demonstrated in Fig. 1. To the best of our knowledge, our CoralVOS is the first dataset and benchmark supporting dense coral video segmentation. We perform experiments on our CoralVOS dataset, including 6 recent state-of-the-art video object segmentation (VOS) algorithms. We fine-tuned these VOS algorithms on our CoralVOS dataset and achieved observable performance improvement. The results show that there is still great potential for further promoting the segmentation accuracy. The dataset and trained models will be released with the acceptance of this work to foster the coral reef research community., Comment: 8 pages, 9 figures, dense coral video segmentation dataset and benchmark

Marine object detection has gained prominence in marine research, driven by the pressing need to unravel oceanic mysteries and enhance our understanding of invaluable marine ecosystems. There is a profound requirement to efficiently and accurately identify and localize diverse and unseen marine entities within underwater imagery. The open-marine object detection (OMOD for short) is required to detect diverse and unseen marine objects, performing categorization and localization simultaneously. To achieve OMOD, we present \textbf{MarineDet}. We formulate a joint visual-text semantic space through pre-training and then perform marine-specific training to achieve in-air-to-marine knowledge transfer. Considering there is no specific dataset designed for OMOD, we construct a \textbf{MarineDet dataset} consisting of 821 marine-relative object categories to promote and measure OMOD performance. The experimental results demonstrate the superior performance of MarineDet over existing generalist and specialist object detection algorithms. To the best of our knowledge, we are the first to present OMOD, which holds a more valuable and practical setting for marine ecosystem monitoring and management. Our research not only pushes the boundaries of marine understanding but also offers a standard pipeline for OMOD., Comment: 8 pages, 5 figures

Omnidirectional camera is a cost-effective and information-rich sensor highly suitable for many marine applications and the ocean scientific community, encompassing several domains such as augmented reality, mapping, motion estimation, visual surveillance, and simultaneous localization and mapping. However, designing and constructing such a high-quality 360$^{\circ}$ real-time streaming camera system for underwater applications is a challenging problem due to the technical complexity in several aspects including sensor resolution, wide field of view, power supply, optical design, system calibration, and overheating management. This paper presents a novel and comprehensive system that addresses the complexities associated with the design, construction, and implementation of a fully functional 360$^{\circ}$ real-time streaming camera system specifically tailored for underwater environments. Our proposed system, UWA360CAM, can stream video in real time, operate in 24/7, and capture 360$^{\circ}$ underwater panorama images. Notably, our work is the pioneering effort in providing a detailed and replicable account of this system. The experiments provide a comprehensive analysis of our proposed system.

Neural radiance field is an emerging rendering method that generates high-quality multi-view consistent images from a neural scene representation and volume rendering. Although neural radiance field-based techniques are robust for scene reconstruction, their ability to add or remove objects remains limited. This paper proposes a new language-driven approach for object manipulation with neural radiance fields through dataset updates. Specifically, to insert a new foreground object represented by a set of multi-view images into a background radiance field, we use a text-to-image diffusion model to learn and generate combined images that fuse the object of interest into the given background across views. These combined images are then used for refining the background radiance field so that we can render view-consistent images containing both the object and the background. To ensure view consistency, we propose a dataset updates strategy that prioritizes radiance field training with camera views close to the already-trained views prior to propagating the training to remaining views. We show that under the same dataset updates strategy, we can easily adapt our method for object insertion using data from text-to-3D models as well as object removal. Experimental results show that our method generates photorealistic images of the edited scenes, and outperforms state-of-the-art methods in 3D reconstruction and neural radiance field blending., Comment: CVPR 2024

In recent years, there has been increasing interest in applying stylization on 3D scenes from a reference style image, in particular onto neural radiance fields (NeRF). While performing stylization directly on NeRF guarantees appearance consistency over arbitrary novel views, it is a challenging problem to guide the transfer of patterns from the style image onto different parts of the NeRF scene. In this work, we propose a stylization framework for NeRF based on local style transfer. In particular, we use a hash-grid encoding to learn the embedding of the appearance and geometry components, and show that the mapping defined by the hash table allows us to control the stylization to a certain extent. Stylization is then achieved by optimizing the appearance branch while keeping the geometry branch fixed. To support local style transfer, we propose a new loss function that utilizes a segmentation network and bipartite matching to establish region correspondences between the style image and the content images obtained from volume rendering. Our experiments show that our method yields plausible stylization results with novel view synthesis while having flexible controllability via manipulating and customizing the region correspondences., Comment: ICCV 2023

360{\deg} images can provide an omnidirectional field of view which is important for stable and long-term scene perception. In this paper, we explore 360{\deg} images for visual object tracking and perceive new challenges caused by large distortion, stitching artifacts, and other unique attributes of 360{\deg} images. To alleviate these problems, we take advantage of novel representations of target localization, i.e., bounding field-of-view, and then introduce a general 360 tracking framework that can adopt typical trackers for omnidirectional tracking. More importantly, we propose a new large-scale omnidirectional tracking benchmark dataset, 360VOT, in order to facilitate future research. 360VOT contains 120 sequences with up to 113K high-resolution frames in equirectangular projection. The tracking targets cover 32 categories in diverse scenarios. Moreover, we provide 4 types of unbiased ground truth, including (rotated) bounding boxes and (rotated) bounding field-of-views, as well as new metrics tailored for 360{\deg} images which allow for the accurate evaluation of omnidirectional tracking performance. Finally, we extensively evaluated 20 state-of-the-art visual trackers and provided a new baseline for future comparisons. Homepage: https://360vot.hkustvgd.com, Comment: ICCV 2023. Homepage: https://360vot.hkustvgd.com The toolkit of the benchmark is available at: https://github.com/HuajianUP/360VOT

In this paper, we address the problem of conditional scene decoration for 360-degree images. Our method takes a 360-degree background photograph of an indoor scene and generates decorated images of the same scene in the panorama view. To do this, we develop a 360-aware object layout generator that learns latent object vectors in the 360-degree view to enable a variety of furniture arrangements for an input 360-degree background image. We use this object layout to condition a generative adversarial network to synthesize images of an input scene. To further reinforce the generation capability of our model, we develop a simple yet effective scene emptier that removes the generated furniture and produces an emptied scene for our model to learn a cyclic constraint. We train the model on the Structure3D dataset and show that our model can generate diverse decorations with controllable object layout. Our method achieves state-of-the-art performance on the Structure3D dataset and generalizes well to the Zillow indoor scene dataset. Our user study confirms the immersive experiences provided by the realistic image quality and furniture layout in our generation results. Our implementation will be made available., Comment: ICCV2023

Building a video retrieval system that is robust and reliable, especially for the marine environment, is a challenging task due to several factors such as dealing with massive amounts of dense and repetitive data, occlusion, blurriness, low lighting conditions, and abstract queries. To address these challenges, we present MarineVRS, a novel and flexible video retrieval system designed explicitly for the marine domain. MarineVRS integrates state-of-the-art methods for visual and linguistic object representation to enable efficient and accurate search and analysis of vast volumes of underwater video data. In addition, unlike the conventional video retrieval system, which only permits users to index a collection of images or videos and search using a free-form natural language sentence, our retrieval system includes an additional Explainability module that outputs the segmentation masks of the objects that the input query referred to. This feature allows users to identify and isolate specific objects in the video footage, leading to more detailed analysis and understanding of their behavior and movements. Finally, with its adaptability, explainability, accuracy, and scalability, MarineVRS is a powerful tool for marine researchers and scientists to efficiently and accurately process vast amounts of data and gain deeper insights into the behavior and movements of marine species., Comment: Accepted to OCEANS 2023 Limerick. Website: https://marinevrs.hkustvgd.com/

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi., Comment: MaCVi 2023 was part of WACV 2023. This report (38 pages) discusses the competition as part of MaCVi

In this paper, we propose a new method for mapping a 3D point cloud to the latent space of a 3D generative adversarial network. Our generative model for 3D point clouds is based on SP-GAN, a state-of-the-art sphere-guided 3D point cloud generator. We derive an efficient way to encode an input 3D point cloud to the latent space of the SP-GAN. Our point cloud encoder can resolve the point ordering issue during inversion, and thus can determine the correspondences between points in the generated 3D point cloud and those in the canonical sphere used by the generator. We show that our method outperforms previous GAN inversion methods for 3D point clouds, achieving state-of-the-art results both quantitatively and qualitatively. Our code is available at https://github.com/hkust-vgd/point_inverter., Comment: WACV 2023 paper. 8 pages of main content, 2 pages of references, 7 pages of supplementary material

Effective analysis of unusual domain specific video collections represents an important practical problem, where state-of-the-art general purpose models still face limitations. Hence, it is desirable to design benchmark datasets that challenge novel powerful models for specific domains with additional constraints. It is important to remember that domain specific data may be noisier (e.g., endoscopic or underwater videos) and often require more experienced users for effective search. In this paper, we focus on single-shot videos taken from moving cameras in underwater environments, which constitute a nontrivial challenge for research purposes. The first shard of a new Marine Video Kit dataset is presented to serve for video retrieval and other computer vision challenges. Our dataset is used in a special session during Video Browser Showdown 2023. In addition to basic meta-data statistics, we present several insights based on low-level features as well as semantic annotations of selected keyframes. The analysis also contains experiments showing limitations of respected general purpose models for retrieval. Our dataset and code are publicly available at https://hkust-vgd.github.io/marinevideokit., Comment: Camera Ready for MMM 2023, Bergen, Norway

Architectural photography is a genre of photography that focuses on capturing a building or structure in the foreground with dramatic lighting in the background. Inspired by recent successes in image-to-image translation methods, we aim to perform style transfer for architectural photographs. However, the special composition in architectural photography poses great challenges for style transfer in this type of photographs. Existing neural style transfer methods treat the architectural images as a single entity, which would generate mismatched chrominance and destroy geometric features of the original architecture, yielding unrealistic lighting, wrong color rendition, and visual artifacts such as ghosting, appearance distortion, or color mismatching. In this paper, we specialize a neural style transfer method for architectural photography. Our method addresses the composition of the foreground and background in an architectural photograph in a two-branch neural network that separately considers the style transfer of the foreground and the background, respectively. Our method comprises a segmentation module, a learning-based image-to-image translation module, and an image blending optimization module. We trained our image-to-image translation neural network with a new dataset of unconstrained outdoor architectural photographs captured at different magic times of a day, utilizing additional semantic information for better chrominance matching and geometry preservation. Our experiments show that our method can produce photorealistic lighting and color rendition on both the foreground and background, and outperforms general image-to-image translation and arbitrary style transfer baselines quantitatively and qualitatively. Our code and data are available at https://github.com/hkust-vgd/architectural_style_transfer., Comment: Updated version with corrected equations. Paper published at the International Conference on Computational Photography (ICCP) 2022. 12 pages of content with 6 pages of supplementary materials

Neural radiance field (NeRF) has recently achieved impressive results in novel view synthesis. However, previous works on NeRF mainly focus on object-centric scenarios. In this work, we propose 360Roam, a novel scene-level NeRF system that can synthesize images of large-scale indoor scenes in real time and support VR roaming. Our system first builds an omnidirectional neural radiance field 360NeRF from multiple input $360^\circ$ images. Using 360NeRF, we then progressively estimate a 3D probabilistic occupancy map which represents the scene geometry in the form of spacial density. Skipping empty spaces and upsampling occupied voxels essentially allows us to accelerate volume rendering by using 360NeRF in a geometry-aware fashion. Furthermore, we use an adaptive divide-and-conquer strategy to slim and fine-tune the radiance fields for further improvement. The floorplan of the scene extracted from the occupancy map can provide guidance for ray sampling and facilitate a realistic roaming experience. To show the efficacy of our system, we collect a $360^\circ$ image dataset in a large variety of scenes and conduct extensive experiments. Quantitative and qualitative comparisons among baselines illustrated our predominant performance in novel view synthesis for complex indoor scenes.

Object reconstruction from 3D point clouds has been a long-standing research problem in computer vision and computer graphics, and achieved impressive progress. However, reconstruction from time-varying point clouds (a.k.a. 4D point clouds) is generally overlooked. In this paper, we propose a new network architecture, namely RFNet-4D++, that jointly reconstructs objects and their motion flows from 4D point clouds. The key insight is simultaneously performing both tasks via learning of spatial and temporal features from a sequence of point clouds can leverage individual tasks, leading to improved overall performance. To prove this ability, we design a temporal vector field learning module using an unsupervised learning approach for flow estimation task, leveraged by supervised learning of spatial structures for object reconstruction. Extensive experiments and analyses on benchmark datasets validated the effectiveness and efficiency of our method. As shown in experimental results, our method achieves state-of-the-art performance on both flow estimation and object reconstruction while performing much faster than existing methods in both training and inference. Our code and data are available at https://github.com/hkust-vgd/RFNet-4D, Comment: TPAMI journal extension of ECCV 2022 arXiv:2203.16482

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point cloud convolutions can be invariant to translation and point permutation, investigations of the rotation invariance property for point cloud convolution has been so far scarce. Some existing methods perform point cloud convolutions with rotation-invariant features, existing methods generally do not perform as well as translation-invariant only counterpart. In this work, we argue that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive. To address this problem, we propose a simple yet effective convolution operator that enhances feature distinction by designing powerful rotation invariant features from the local regions. We consider the relationship between the point of interest and its neighbors as well as the internal relationship of the neighbors to largely improve the feature descriptiveness. Our network architecture can capture both local and global context by simply tuning the neighborhood size in each convolution layer. We conduct several experiments on synthetic and real-world point cloud classifications, part segmentation, and shape retrieval to evaluate our method, which achieves the state-of-the-art accuracy under challenging rotations., Comment: Authors' version. Accepted to International Journal of Computer Vision (IJCV) 2022

The huge domain gap between sketches and photos and the highly abstract sketch representations pose challenges for sketch-based image retrieval (\underline{SBIR}). The zero-shot sketch-based image retrieval (\underline{ZS-SBIR}) is more generic and practical but poses an even greater challenge because of the additional knowledge gap between the seen and unseen categories. To simultaneously mitigate both gaps, we propose an \textbf{A}pproaching-and-\textbf{C}entralizing \textbf{Net}work (termed "\textbf{ACNet}") to jointly optimize sketch-to-photo synthesis and the image retrieval. The retrieval module guides the synthesis module to generate large amounts of diverse photo-like images which gradually approach the photo domain, and thus better serve the retrieval module than ever to learn domain-agnostic representations and category-agnostic common knowledge for generalizing to unseen categories. These diverse images generated with retrieval guidance can effectively alleviate the overfitting problem troubling concrete category-specific training samples with high gradients. We also discover the use of proxy-based NormSoftmax loss is effective in the zero-shot setting because its centralizing effect can stabilize our joint training and promote the generalization ability to unseen categories. Our approach is simple yet effective, which achieves state-of-the-art performance on two widely used ZS-SBIR datasets and surpasses previous methods by a large margin., Comment: the paper is accepted by IEEE Transactions on Circuits and Systems for Video Technology, please refer https://ieeexplore.ieee.org/document/10052737 for an updated version

Furnishing and rendering indoor scenes has been a long-standing task for interior design, where artists create a conceptual design for the space, build a 3D model of the space, decorate, and then perform rendering. Although the task is important, it is tedious and requires tremendous effort. In this paper, we introduce a new problem of domain-specific indoor scene image synthesis, namely neural scene decoration. Given a photograph of an empty indoor space and a list of decorations with layout determined by user, we aim to synthesize a new image of the same space with desired furnishing and decorations. Neural scene decoration can be applied to create conceptual interior designs in a simple yet effective manner. Our attempt to this research problem is a novel scene generation architecture that transforms an empty scene and an object layout into a realistic furnished scene photograph. We demonstrate the performance of our proposed method by comparing it with conditional image synthesis baselines built upon prevailing image translation approaches both qualitatively and quantitatively. We conduct extensive experiments to further validate the plausibility and aesthetics of our generated scenes. Our implementation is available at \url{https://github.com/hkust-vgd/neural_scene_decoration}., Comment: ECCV 2022 paper. 14 pages of main content, 4 pages of references, and 11 pages of appendix

SLAM (Simultaneous Localization And Mapping) seeks to provide a moving agent with real-time self-localization. To achieve real-time speed, SLAM incrementally propagates position estimates. This makes SLAM fast but also makes it vulnerable to local pose estimation failures. As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle. This paper attempts to correct this problem. We note that while local pose estimation is ill-conditioned, pose estimation over longer sequences is well-conditioned. Thus, local pose estimation errors eventually manifest themselves as mapping inconsistencies. When this occurs, we save the current map and activate two new SLAM threads. One processes incoming frames to create a new map and the other, recovery thread, backtracks to link new and old maps together. This creates a Dual-SLAM framework that maintains real-time performance while being robust to local pose estimation failures. Evaluation on benchmark datasets shows Dual-SLAM can reduce failures by a dramatic $88\%$., Comment: Accepted by International Conference on Intelligent Robots and Systems (IROS) 2020

With recent developments of convolutional neural networks, deep learning for 3D point clouds has shown significant progress in various 3D scene understanding tasks, e.g., object recognition, semantic segmentation. In a safety-critical environment, it is however not well understood how such deep learning models are vulnerable to adversarial examples. In this work, we explore adversarial attacks for point cloud-based neural networks. We propose a unified formulation for adversarial point cloud generation that can generalise two different attack strategies. Our method generates adversarial examples by attacking the classification ability of point cloud-based networks while considering the perceptibility of the examples and ensuring the minimal level of point manipulations. Experimental results show that our method achieves the state-of-the-art performance with higher than 89% and 90% of attack success rate on synthetic and real-world data respectively, while manipulating only about 4% of the total points., Comment: ICCV 2021 camera-ready paper (8 pages)

Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data, however, could have arbitrary rotations, especially those acquired from 3D scanning. Recent works show that it is possible to design point cloud convolutions with rotation invariance property, but such methods generally do not perform as well as translation-invariant only convolution. We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive. To address this problem, we propose a novel convolution operator that enhances feature distinction by integrating global context information from the input point cloud to the convolution. To this end, a globally weighted local reference frame is constructed in each point neighborhood in which the local point set is decomposed into bins. Anchor points are generated in each bin to represent global shape features. A convolution can then be performed to transform the points and anchor features into final rotation-invariant features. We conduct several experiments on point cloud classification, part segmentation, shape retrieval, and normals estimation to evaluate our convolution, which achieves state-of-the-art accuracy under challenging rotations.

Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic methods allowing minimal effort from users to guide computer algorithms are often preferred due to desirable accuracy and performance. Inspired by the practicality and applicability of the semi-automatic approach, this paper proposes a novel deep neural network architecture, namely SideInfNet that effectively integrates features learnt from images with side information extracted from user annotations. To evaluate our method, we applied the proposed network to three semantic segmentation tasks and conducted extensive experiments on benchmark datasets. Experimental results and comparison with prior work have verified the superiority of our model, suggesting the generality and effectiveness of the model in semi-automatic semantic segmentation., Comment: ECCV 2020

In this work, we present a novel method to learn a local cross-domain descriptor for 2D image and 3D point cloud matching. Our proposed method is a dual auto-encoder neural network that maps 2D and 3D input into a shared latent space representation. We show that such local cross-domain descriptors in the shared embedding are more discriminative than those obtained from individual training in 2D and 3D domains. To facilitate the training process, we built a new dataset by collecting $\approx 1.4$ millions of 2D-3D correspondences with various lighting conditions and settings from publicly available RGB-D scenes. Our descriptor is evaluated in three main experiments: 2D-3D matching, cross-domain retrieval, and sparse-to-dense depth estimation. Experimental results confirm the robustness of our approach as well as its competitive performance not only in solving cross-domain tasks but also in being able to generalize to solve sole 2D and 3D tasks. Our dataset and code are released publicly at \url{https://hkust-vgd.github.io/lcd}., Comment: Accepted to AAAI 2020 (Oral)

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks being trained with data augmented with rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the convolution. This convolution operator then serves as the basic building block of a neural network that is robust to point clouds under 6DoF transformations such as translation and rotation. Our experiment shows that our method performs with high accuracy in common scene understanding tasks such as object classification and segmentation. Compared to previous works, most importantly, our method is able to generalize and achieve consistent results across different scenarios in which training and testing can contain arbitrary rotations., Comment: International Conference on 3D Vision (3DV) 2019

Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data. While being able to achieve good accuracies in various scene understanding tasks, previous methods often have low training speed and complex network architecture. In this paper, we address these problems by proposing an efficient end-to-end permutation invariant convolution for point cloud deep learning. Our simple yet effective convolution operator named ShellConv uses statistics from concentric spherical shells to define representative features and resolve the point order ambiguity, allowing traditional convolution to perform on such features. Based on ShellConv we further build an efficient neural network named ShellNet to directly consume the point clouds with larger receptive fields while maintaining less layers. We demonstrate the efficacy of ShellNet by producing state-of-the-art results on object classification, object part segmentation, and semantic scene segmentation while keeping the network very fast to train., Comment: International Conference on Computer Vision (ICCV) 2019 Oral

Deep learning techniques for point cloud data have demonstrated great potentials in solving classical problems in 3D computer vision such as 3D object classification and segmentation. Several recent 3D object classification methods have reported state-of-the-art performance on CAD model datasets such as ModelNet40 with high accuracy (~92%). Despite such impressive results, in this paper, we argue that object classification is still a challenging task when objects are framed with real-world settings. To prove this, we introduce ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data. From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions. We identify three key open problems for point cloud object classification, and propose new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background. Our dataset and code are publicly available in our project page https://hkust-vgd.github.io/scanobjectnn/., Comment: ICCV 2019 Oral

Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address the problems of semantic and instance segmentation of 3D point clouds. Specifically, we develop a multi-task pointwise network that simultaneously performs two tasks: predicting the semantic classes of 3D points and embedding the points into high-dimensional vectors so that points of the same object instance are represented by similar embeddings. We then propose a multi-value conditional random field model to incorporate the semantic and instance labels and formulate the problem of semantic and instance segmentation as jointly optimising labels in the field model. The proposed method is thoroughly evaluated and compared with existing methods on different indoor scene datasets including S3DIS and SceneNN. Experimental results showed the robustness of the proposed joint semantic-instance segmentation scheme over its single components. Our method also achieved state-of-the-art performance on semantic segmentation., Comment: CVPR 2019 (Oral). More information at https://pqhieu.github.io/cvpr19.html

The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense reconstruction and semantic segmentation of 3D indoor scenes. To guarantee (near) real-time performance, our method is built atop an efficient super-voxel clustering method and a conditional random field with higher-order constraints from structural and object cues, enabling progressive dense semantic segmentation without any precomputation. We extensively evaluate our method on different indoor scenes including kitchens, offices, and bedrooms in the SceneNN and ScanNet datasets and show that our technique consistently produces state-of-the-art segmentation results in both qualitative and quantitative experiments., Comment: WACV 2019. More information at https://pqhieu.github.io/wacv19.html

Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored. In this paper, we present a convolutional neural network for semantic segmentation and object recognition with 3D point clouds. At the core of our network is pointwise convolution, a new convolution operator that can be applied at each point of a point cloud. Our fully convolutional network design, while being surprisingly simple to implement, can yield competitive accuracy in both semantic segmentation and object recognition task., Comment: 10 pages, 6 figures, 10 tables. Paper accepted to CVPR 2018

Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data. Such data, if completely and well annotated, can serve as useful ingredients for a wide spectrum of computer vision and graphics works such as data-driven modeling and scene understanding, object detection and recognition. However, annotating a vast amount of 3D scene data remains challenging due to the lack of an effective tool and/or the complexity of 3D scenes (e.g. clutter, varying illumination conditions). This paper aims to build a robust annotation tool that effectively and conveniently enables the segmentation and annotation of massive 3D data. Our tool works by coupling 2D and 3D information via an interactive framework, through which users can provide high-level semantic annotation for objects. We have experimented our tool and found that a typical indoor scene could be well segmented and annotated in less than 30 minutes by using the tool, as opposed to a few hours if done manually. Along with the tool, we created a dataset of over a hundred 3D scenes associated with complete annotations using our tool. The tool and dataset are available at www.scenenn.net., Comment: 14 pages

We present a portable device to capture both shape and reflectance of an indoor scene. Consisting of a Kinect, an IR camera and several IR LEDs, our device allows the user to acquire data in a similar way as he/she scans with a single Kinect. Scene geometry is reconstructed by KinectFusion. To estimate reflectance from incomplete and noisy observations, 3D vertices of the same material are identified by our material segmentation propagation algorithm. Then BRDF observations at these vertices are merged into a more complete and accurate BRDF for the material. Effectiveness of our device is demonstrated by quality results on real-world scenes.