Zhou Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhou Wang has a total of 128 co-authors. Here are the top co-authors by number of shared publications:
- Honglei Su
Qingdao University
8 shared publications - Hui Yuan
Shandong University
7 shared publications - Qi Liu
Qingdao University
7 shared publications - Zhengfang Duanmu
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada
6 shared publications - Yuming Fang
Jiangxi University of Finance and Economics, Nanchang, China
5 shared publications - Wentao Liu
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
4 shared publications
Latest Publications
- 25 September 2026
- Published byĀ Springer Nature
- p. 120-130
Automated Disentangling Analysis of Skin Colour for Lesion Images
- 25 September 2026
- Published byĀ Springer Nature
- p. 120-130
Automated Disentangling Analysis of Skin Colour for Lesion Images
- 9 July 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā PP, 7363-7374
Perceptual Geometry Distortion Assessment of Compressed 3D Meshes.
The evaluation of perceptual quality in 3D mesh compression, particularly for Video-based Dynamic Mesh Coding (V-DMC), is challenged by the scarcity of subject-rated datasets and the high computational cost of full-mesh decoding and the sophisticated visual feature extraction steps. To bridge this gap, we first introduce a novel V-DMC distortion dataset, comprising 16 high-quality original meshes and 400 compressed, textureless variants. We conducted a subjective quality assessment study with 30 participants using the Double Stimulus Impairment Scale (DSIS) method to collect reliable Mean Opinion Scores (MOS). We then propose streamMQ, the first-of-its-kind noreference, bitstream-layer model for perceptual quality assessment of V-DMC compressed meshes. By extracting key geometric features such as quantization parameters and triangle count directly from the compressed bitstream, streamMQ predicts perceptual quality without full decoding. Experimental evaluation and comparison with state-of-the-art methods demonstrate that streamMQ achieves highly competitive quality assessment performance at tiny fractions of computational and storage costs, facilitating real-time and low-storage application environments. The dataset and source code will be made publicly available at https://github.com/HFL01/QDU-GDM.
- 9 July 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā PP, 7363-7374
Perceptual Geometry Distortion Assessment of Compressed 3D Meshes.
The evaluation of perceptual quality in 3D mesh compression, particularly for Video-based Dynamic Mesh Coding (V-DMC), is challenged by the scarcity of subject-rated datasets and the high computational cost of full-mesh decoding and the sophisticated visual feature extraction steps. To bridge this gap, we first introduce a novel V-DMC distortion dataset, comprising 16 high-quality original meshes and 400 compressed, textureless variants. We conducted a subjective quality assessment study with 30 participants using the Double Stimulus Impairment Scale (DSIS) method to collect reliable Mean Opinion Scores (MOS). We then propose streamMQ, the first-of-its-kind noreference, bitstream-layer model for perceptual quality assessment of V-DMC compressed meshes. By extracting key geometric features such as quantization parameters and triangle count directly from the compressed bitstream, streamMQ predicts perceptual quality without full decoding. Experimental evaluation and comparison with state-of-the-art methods demonstrate that streamMQ achieves highly competitive quality assessment performance at tiny fractions of computational and storage costs, facilitating real-time and low-storage application environments. The dataset and source code will be made publicly available at https://github.com/HFL01/QDU-GDM.
- 17 March 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā 35 Ā (10577149) , 3594-3608
Attention Redundancy Reduction for Image Super-Resolution
Transformer-based models have demonstrated great promises in single image super-resolution (SISR), but our investigations find significant redundancy in terms of high mutual information across the attention maps, negatively impacting both the quality and efficiency performance of SOTA models. To address the problem, here we propose a low redundancy attention network (LRAN). First, to mitigate the redundancy among heads, we introduce in the self-attention computation a multi-element mechanism, which allows for the incorporation of various types of self-attention, thus increasing inter-head diversity. Second, to address the redundancy among blocks, we propose the encapsulated architecture, in which enhanced local perception unit and gated multi-layer perceptron are designed to capture local information. Specifically, this architecture incorporates a single self-attention layer between several MLP layers. Subsequently, the proposed gated multi-layer perceptron significantly enhances the SR quality. Extensive experiments demonstrate that LRAN outperforms SOTA models in the task of lightweight SR, achieving a better trade-off between quality and speed. For instance, the proposed LRAN-light surpasses SwinIR-light by 0.32dB PSNR in Ć4 SR on Urban100, while running Ć4 faster.
- 17 March 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā 35 Ā (10577149) , 3594-3608
Attention Redundancy Reduction for Image Super-Resolution
Transformer-based models have demonstrated great promises in single image super-resolution (SISR), but our investigations find significant redundancy in terms of high mutual information across the attention maps, negatively impacting both the quality and efficiency performance of SOTA models. To address the problem, here we propose a low redundancy attention network (LRAN). First, to mitigate the redundancy among heads, we introduce in the self-attention computation a multi-element mechanism, which allows for the incorporation of various types of self-attention, thus increasing inter-head diversity. Second, to address the redundancy among blocks, we propose the encapsulated architecture, in which enhanced local perception unit and gated multi-layer perceptron are designed to capture local information. Specifically, this architecture incorporates a single self-attention layer between several MLP layers. Subsequently, the proposed gated multi-layer perceptron significantly enhances the SR quality. Extensive experiments demonstrate that LRAN outperforms SOTA models in the task of lightweight SR, achieving a better trade-off between quality and speed. For instance, the proposed LRAN-light surpasses SwinIR-light by 0.32dB PSNR in Ć4 SR on Urban100, while running Ć4 faster.
- Open Access
Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints with superior framing and composition compared to existing approaches, establishing a new direction toward 3D-aware aesthetic modeling.
Open AccessAesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints with superior framing and composition compared to existing approaches, establishing a new direction toward 3D-aware aesthetic modeling.
- 1 January 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā 35, 11216-11227
SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-Supervised No-Reference Image Quality Assessment
No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a pristine reference. Learning an NR-IQA model faces a fundamental bottleneck because it requires many costly human perceptual labels. We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images through explicitly structured relational supervision. Unlike prior methods that impose rigid binary similarity constraints, SHAMISA shapes soft, controllable implicit structural associations that are both distortion-aware and content-sensitive. A key innovation is its compositional distortion engine, which generates an uncountable family of degradations from continuous parameter spaces and groups the resulting images so that exactly one distortion factor varies at a time. This construction enables fine-grained control over representational similarity during training. Images with shared distortion patterns are pulled together in the embedding space, while severity variations produce structured shifts. Dual-source relation graphs integrate known degradation profiles with emergent structural affinities throughout pre-training. The learned encoder is then frozen and paired with a linear regressor. Extensive experiments on synthetic, authentic, and cross-dataset NR-IQA benchmarks demonstrate strong overall performance, improved transfer in the reported cross-dataset comparisons, and favorable qualitative robustness diagnostics. Self-supervised pre-training requires no IQA opinion-score annotations or contrastive loss.
- 1 January 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā 35, 11216-11227
SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-Supervised No-Reference Image Quality Assessment
No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a pristine reference. Learning an NR-IQA model faces a fundamental bottleneck because it requires many costly human perceptual labels. We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images through explicitly structured relational supervision. Unlike prior methods that impose rigid binary similarity constraints, SHAMISA shapes soft, controllable implicit structural associations that are both distortion-aware and content-sensitive. A key innovation is its compositional distortion engine, which generates an uncountable family of degradations from continuous parameter spaces and groups the resulting images so that exactly one distortion factor varies at a time. This construction enables fine-grained control over representational similarity during training. Images with shared distortion patterns are pulled together in the embedding space, while severity variations produce structured shifts. Dual-source relation graphs integrate known degradation profiles with emergent structural affinities throughout pre-training. The learned encoder is then frozen and paired with a linear regressor. Extensive experiments on synthetic, authentic, and cross-dataset NR-IQA benchmarks demonstrate strong overall performance, improved transfer in the reported cross-dataset comparisons, and favorable qualitative robustness diagnostics. Self-supervised pre-training requires no IQA opinion-score annotations or contrastive loss.
- 1 January 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Broadcasting
- p. 1-15
Perceptual Quality Assessment of Octree-RAHT Encoded 3-D Point Clouds
- 1 January 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Broadcasting
- p. 1-15
Perceptual Quality Assessment of Octree-RAHT Encoded 3-D Point Clouds
- 5 November 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Visualization and Computer Graphics
- Vol.Ā 32 Ā (2) , 2034-2048
Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds
No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we develop the first PCQA model dedicated to Trisoup-Lifting encoded 3D point clouds by analyzing bitstreams without full decoding. Specifically, we investigate the relationship among texture bitrate per point (TBPP), texture complexity (TC) and texture quantization parameter (TQP) while geometry encoding is lossless. Subsequently, we estimate TC by utilizing TQP and TBPP. Then, we establish a texture distortion evaluation model based on TC, TBPP and TQP. Ultimately, by integrating this texture distortion model with a geometry attenuation factor, a function of trisoupNodeSizeLog2 (tNSL), we acquire a comprehensive NR bitstream-layer PCQA model named streamPCQ-TL. In addition, this work establishes a database named WPC6.0, the first PCQA database dedicated to Trisoup-Lifting encoding mode, encompassing 400 distorted point clouds with 4 geometry multiplied by 5 texture distortion levels. Experiment results on M-PCCD, ICIP2020 and the proposed WPC6.0 database suggest that the proposed streamPCQ-TL model exhibits robust and notable performance in contrast to existing advanced PCQA metrics, particularly in terms of computational cost. The dataset and source code will be publicly released at https://github.com/qdushl/Waterloo-Point-Cloud-Database-6.0.
- 5 November 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Visualization and Computer Graphics
- Vol.Ā 32 Ā (2) , 2034-2048
Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds
No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we develop the first PCQA model dedicated to Trisoup-Lifting encoded 3D point clouds by analyzing bitstreams without full decoding. Specifically, we investigate the relationship among texture bitrate per point (TBPP), texture complexity (TC) and texture quantization parameter (TQP) while geometry encoding is lossless. Subsequently, we estimate TC by utilizing TQP and TBPP. Then, we establish a texture distortion evaluation model based on TC, TBPP and TQP. Ultimately, by integrating this texture distortion model with a geometry attenuation factor, a function of trisoupNodeSizeLog2 (tNSL), we acquire a comprehensive NR bitstream-layer PCQA model named streamPCQ-TL. In addition, this work establishes a database named WPC6.0, the first PCQA database dedicated to Trisoup-Lifting encoding mode, encompassing 400 distorted point clouds with 4 geometry multiplied by 5 texture distortion levels. Experiment results on M-PCCD, ICIP2020 and the proposed WPC6.0 database suggest that the proposed streamPCQ-TL model exhibits robust and notable performance in contrast to existing advanced PCQA metrics, particularly in terms of computational cost. The dataset and source code will be publicly released at https://github.com/qdushl/Waterloo-Point-Cloud-Database-6.0.
- 31 October 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol.Ā 48 Ā (3) , 2581-2595
Structural Similarity in Deep Features: Unified Image Quality Assessment Robust to Geometrically Disparate Reference
Image Quality Assessment (IQA) with references plays an important role in optimizing and evaluating computer vision tasks. Traditional methods assume that all pixels of the reference and test images are fully aligned. Such Aligned-Reference IQA (AR-IQA) approaches fail to address many real-world problems with various geometric deformations between the two images. Although significant effort has been made to attack Geometrically-Disparate-Reference IQA (GDR-IQA) problem, it has been addressed in a task-dependent fashion, for example, by dedicated designs for image super-resolution and retargeting, or by assuming the geometric distortions to be small that can be countered by translation-robust filters or by explicit image registrations. Here we rethink this problem and propose a unified, non-training-based Deep Structural Similarity (DeepSSIM) approach to address the above problems in a single framework, which assesses structural similarity of deep features in a simple but efficient way and uses an attention calibration strategy to alleviate attention deviation. The proposed method, without application-specific design, achieves state-of-the-art performance on AR-IQA datasets and meanwhile shows strong robustness to various GDR-IQA test cases. Interestingly, our test also shows the effectiveness of DeepSSIM as an optimization tool for training image super-resolution, enhancement and restoration, implying an even wider generalizability.
- 31 October 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol.Ā 48 Ā (3) , 2581-2595
Structural Similarity in Deep Features: Unified Image Quality Assessment Robust to Geometrically Disparate Reference
Image Quality Assessment (IQA) with references plays an important role in optimizing and evaluating computer vision tasks. Traditional methods assume that all pixels of the reference and test images are fully aligned. Such Aligned-Reference IQA (AR-IQA) approaches fail to address many real-world problems with various geometric deformations between the two images. Although significant effort has been made to attack Geometrically-Disparate-Reference IQA (GDR-IQA) problem, it has been addressed in a task-dependent fashion, for example, by dedicated designs for image super-resolution and retargeting, or by assuming the geometric distortions to be small that can be countered by translation-robust filters or by explicit image registrations. Here we rethink this problem and propose a unified, non-training-based Deep Structural Similarity (DeepSSIM) approach to address the above problems in a single framework, which assesses structural similarity of deep features in a simple but efficient way and uses an attention calibration strategy to alleviate attention deviation. The proposed method, without application-specific design, achieves state-of-the-art performance on AR-IQA datasets and meanwhile shows strong robustness to various GDR-IQA test cases. Interestingly, our test also shows the effectiveness of DeepSSIM as an optimization tool for training image super-resolution, enhancement and restoration, implying an even wider generalizability.
- 15 July 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā PP Ā (10577149) , 1
Perceptual Quality Assessment of 360° Images Based on Generative Scanpath Representation
Despite substantial efforts dedicated to the design of heuristic models for omnidirectional (i.e., 360°) image quality assessment (OIQA), a conspicuous gap remains due to the lack of consideration for the diversity of viewing behaviors that leads to the varying perceptual quality of 360° images. Two critical aspects underline this oversight: the neglect of viewing conditions that significantly sway user gaze patterns and the overreliance on a single viewport sequence from the 360° image for quality inference. To address these issues, we introduce a unique generative scanpath representation (GSR) for effective quality inference of 360° images, which aggregates varied perceptual experiences of multi-hypothesis users under a predefined viewing condition. More specifically, given a viewing condition characterized by the starting point of viewing and exploration time, a set of scanpaths consisting of dynamic visual fixations can be produced using an apt scanpath generator. Following this vein, we use the scanpaths to convert the 360° image into the unique GSR, which provides a global overview of gazed-focused contents derived from scanpaths. As such, the quality inference of the 360° image is swiftly transformed to that of GSR. We then propose an efficient OIQA computational framework by learning the quality maps of GSR. Comprehensive experimental results validate that the predictions of the proposed framework are highly consistent with human perception in the spatiotemporal domain, especially in the challenging context of locally distorted 360° images under varied viewing conditions. The code will be released at https://github.com/xiangjieSui/GSR.
- 15 July 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Image Processing
- Vol.Ā PP Ā (10577149) , 1
Perceptual Quality Assessment of 360° Images Based on Generative Scanpath Representation
Despite substantial efforts dedicated to the design of heuristic models for omnidirectional (i.e., 360°) image quality assessment (OIQA), a conspicuous gap remains due to the lack of consideration for the diversity of viewing behaviors that leads to the varying perceptual quality of 360° images. Two critical aspects underline this oversight: the neglect of viewing conditions that significantly sway user gaze patterns and the overreliance on a single viewport sequence from the 360° image for quality inference. To address these issues, we introduce a unique generative scanpath representation (GSR) for effective quality inference of 360° images, which aggregates varied perceptual experiences of multi-hypothesis users under a predefined viewing condition. More specifically, given a viewing condition characterized by the starting point of viewing and exploration time, a set of scanpaths consisting of dynamic visual fixations can be produced using an apt scanpath generator. Following this vein, we use the scanpaths to convert the 360° image into the unique GSR, which provides a global overview of gazed-focused contents derived from scanpaths. As such, the quality inference of the 360° image is swiftly transformed to that of GSR. We then propose an efficient OIQA computational framework by learning the quality maps of GSR. Comprehensive experimental results validate that the predictions of the proposed framework are highly consistent with human perception in the spatiotemporal domain, especially in the challenging context of locally distorted 360° images under varied viewing conditions. The code will be released at https://github.com/xiangjieSui/GSR.