Wenhui Zhou Professor, SM IEEE School of Computer Science and Technology, Hangzhou Dianzi University (HDU). He received a Ph.D. degree in information and communication engineering from Zhejiang University (ZJU) in 2005, and then worked as a postdoctoral researcher in the Department of Information Science and Electronic Engineering (ISEE) at ZJU from July 2005 to October 2007. During his doctoral studies and postdoctoral research, he followed Prof. Weikang Gu and Prof. Jilin Liu to conduct research on autonomous driving and visual navigation systems. He joined the School of Computer Science and Technology at Hangzhou Dianzi University (HDU) as an Assistant Professor in 2007, and was promoted to Associate Professor and Professor in 2008 and 2021, respectively. From April 2015 to April 2016, he was a visiting scholar at Indiana University Bloomington, working with Prof. Andrew Lumsdaine to conduct research in the field of light field imaging and processing. His research interests lie in the general areas of computer vision, computational photography, brain-computer interface, machine learning, etc. His current work focuses on deep learning for image/video understanding and visual brain-computer interface. He is a senior member of IEEE.
2021.01-Now Professor, Hangzhou Dianzi University. School of Computer Science and Technology. 2015.04-2016.04 Visiting Scholar, Indiana University Bloomington, USA. School of Informatics, Computing, and Engineering. 2008.09-2020.12 Associate Professor, Hangzhou Dianzi University. School of Computer Science and Technology. 2007.10-2008.09 Assistant Professor, Hangzhou Dianzi University. School of Computer Science and Technology. 2005.06-2007.10 Assistant Professor & PostDoc, Zhejiang University. College of Information Science & Electronic Engineering. 2002.09-2005.06 Ph.D., Zhejiang University. College of Information Science & Electronic Engineering.
Selected Projects： National Natural Science Foundation of China. Continuous Domain Representation and Rendering and Evaluation of Dynamic Light Field for Digital-Real Fusion and Virtual-Real Symbiosis. Co-Principle Investigator (2/3). Grant No. 62471437. 2025-01 to 2028-12, ￥510,000 RMB. Key Joint Funds Program of Zhejiang Provincial Natural Science Foundation of China. Research on Perception Fusion and Autonomous Navigation Technology for Industrial Drones in Complex Mountainous Environments. Co-Principle Investigator (5/7). Grant No. LLSSZ24F020001. 2024-01 to 2026-12, ￥300,000 RMB. Key Scientific Research Program of Hangzhou. Multimodal Biometric Technology and Its Applications. Co-Principle Investigator (2/64). PI of HDU. Grant No. 2024SZD1B01. 2024-01 to 2025-12, ￥3,000,000 RMB.
Key Scientific Research Program of Hangzhou. Deep Learning based Indigenous Intelligent High-Definition Video Processing Chip for Network Digital Applications. Co-Principle Investigator (4/59), PI of HDU. Grant No. 2022AIZD0095. 2023-01 to 2025-6, ￥5,000,000 RMB. Joint Funds Program of the Zhejiang Provincial Natural Science Foundation of China. Quality Evaluation and Optimization of High Dynamic Light Field Video for Medical Immersive Imaging. Principle Investigator. Grant No. LTY22F020001. 2022.1- 2024.12. ￥100,000 RMB.
National Key Research and Development Program of China. Security Risk Intelligent Perception Engine Technology for Social Governance. Co-Principle Investigator (4/25). Grant No. 2021YFC3320301. 2021.12-2024.11. ￥5,000,000 RMB. Zhejiang Provincial Natural Science Foundation of China. Unsupervised Learning based 3D Modeling from Multi-view Light Field Sequence. Co-Principle Investigator (2/5). Grant No. LY21F010007. 2021.1-2023.12. ￥100,000 RMB. National Key Research and Development Program of China. Research on Key Technologies of EEG based Safe Driving Warning and Simulation Platform. Co-Principle Investigator (9/25). Grant No. 2017YFE0118200. 2019.1-2022.12. ￥3,910,000 RMB. National High-tech Research and Development Program of China (subproject of 863 Program). Research on Light Field based True 3D Video Acquisition and Generation. Principle Investigator. Grant No. 2015AA015901. 2015.1-2018.12. ￥725,000 RMB. Key Program of Zhejiang Provincial Natural Science Foundation of China. Research on Key Factors of 3D Multimode Bone Injury Image Registration and Fusion. Principle Investigator. Grant No. LZ14F020003. 2014.1-2017.12. ￥360,000 RMB. National Natural Science Foundation of China. Research on Stereo Imaging Theory and High-accuracy 3D Modeling with Binocular Plenoptic Cameras. Co-Principle Investigator (2/7). Grant No. 61102146. 2012.1-2014.12. ￥270,000 RMB. National Natural Science Foundation of China of China: Study on Invariant Cognition Based Binocular Visual Attention. Principle Investigator. Grant No. 60902077. 2010.1-2012.12. ￥250,000 RMB. Zhejiang Province Social Development Projects of Major Science and Technology Projects of China: Study on Multi-level Intelligent Transportation Integrated Information Network Architecture and Its Key Techniques. Principle Investigator. Grant No. 2008C13076. 2008.10-2011.12. ￥800,000 RMB. Zhejiang Provincial Natural Science Foundation of China: Large Scale Multiple Viewpoint Reconstruction and Information Fusion for 3D Digital City Modeling. Principle Investigator. Grant No.Y1080967. 2009.1-2010.12. ￥80,000 RMB.
======== Some Photos of Selected Prototype Systems ======== It uses a real "Zhidou D2S" electric vehicle as the base platform, on which all subsystems (including the accelerator pedal, brake pedal, steering wheel, gear shifting mechanism, etc.) are retained except the power subsystem. Moreover, we also install several relevant sensors and their embedded systems to obtain the operation and control signals during simulated driving. In addition, an 180° cylindrical screen projection system had been designed for immersive experience.  
 
It can accurately control the angle and position of the rotating platform and camera bracket through a computer, and provide synchronous control between the light source and the camera.  
It is a large visual dome with a diameter of 10 meters and a height of 7 meters, which equipped up to 60 cameras and 2000 LED lights.  
 
Transverse scientific research
Publications
Selected Journal Papers： Junle Yu, Wenhui Zhou, Zhehao Shen and Yongwei Miao, EfficientPEAL: Efficient prior-embedded attention learning for partially overlapping point cloud registration. Expert Systems With Applications, 2025. 293: 128591. Xin Xiang, Wenhui Zhou*, Guojun Dai. Electroencephalography-Driven Three-Dimensional Object Decoding with Multi-view Perception Diffusion. Engineering Applications of Artificial Intelligence. 2025. 156 (Part C): 111180. [code is coming soon] Hao Zhang, Wenhui Zhou*, Lili Lin, Andrew Lumsdaine. Cascade Residual Learning based Adaptive Feature Aggregation for Light Field Super-resolution. Pattern Recognition. 2025. 165: 111616. [code is coming soon] Wenhui Zhou, Luwei Ren, Junle Yu*, Nian Qu, Guojun Dai*. Boosting RGB-D Point Cloud Registration via Explicit Position-Aware Geometric Embedding. IEEE Robotics and Automation Letters. 2024, 9(6): 5839--5846. [code]
Wenhui Zhou, Yuhan Wang, Liangyan Mo, Changsheng Li, Mingyue Xu, Wanzeng Kong, Guojun Dai. Temporal-Channel Cascaded Transformer for Imagined Handwriting Character Recognition. Neurocomputing. 2024. 573: 127243. [code]
Wenhui Zhou, Lili Lin*, Yongjie Hong, Qiujian Li, Xingfa Shen* and Ercan Engin Kuruoglu. Beyond Photometric Consistency: Geometry-based Occlusion-aware Unsupervised Light Field Disparity Estimation. IEEE Transactions on Neural Networks and Learning Systems, 2024. 35(11): 15660--15674. [code][ MP4] Lili Lin, Siyu Bai, Mengjia Qu, Xuehui Wei*, Luyao Wang, Feifan Wu, Biao Liu, Wenhui Zhou*, Ercan Engin Kuruoglu. Transformer-based Light Field Geometry Learning for No-reference Light Field Image Quality Assessment. IEEE Transactions on Broadcasting. 2024. 70(2): 597-606. [code]
Lili Lin, Mengjia Qu, Siyu Bai, Luyao Wang, Xuehui Wei*, Wenhui Zhou*. Feature-level Contrastive Learning for Full-Reference Light Field Image Quality Assessment. Journal of the Franklin Institute. 2024, 361(14): 107058. [code]
Jingtao Wu, Guojun Dai, Wenhui Zhou*, Xudong Zhu, Zengguan Wang. Multi-scale Feature Fusion with Attention Mechanism for Crowded Road Object Detection. Journal of Real-Time Image Processing. 2024. 21(29): 1-12.
Wenhui Zhou, Hua Zhang, Zhengmao Yan, Weisheng Wang, and Lili Lin. DecoupledPoseNet: Cascade Decoupled Pose Learning for Unsupervised Camera Ego-motion Estimation. IEEE Transactions on Multimedia, 2023. 25: 1636-1648.[code] Wenhui Zhou, Jinyu Liu, Jiefeng Li, Jiyi Li, Lili Lin*, Fumiyo Fukumoto, Guojun Dai*, Style-independent Radical Sequence Learning for Zero-shot Recognition of Small Seal Script. Journal of the Franklin Institute. 2023. 360(16): 11295-11313. [code] Mingyue Xu, Wenhui Zhou*, Xingfa Shen*, Yuhan Wang, Liangyan Mo, Junping Qiu. Swin-TCNet: Swin-based Temporal-Channel Cascade Network for Motor Imagery iEEG Signal Recognition. Biomedical Signal Processing and Control. 2023. 85: 104885. Wenxuan Yang, Chenghao Tan, Yuxin Chen, Huang Xia, Xuexi Tang, Yifan Cao, Wenhui Zhou, Lili Lin, and Guojun Dai, BiRSwinT: Bilinear Full-Scale Residual Swin-Transformer for Fine-Grained Driver Behavior Recognition. Journal of the Franklin Institute, 2023. 360(2): 1166-1183. [code] Lili Lin, Qiujian Li, Bin Gao, Yuxiang Yan, Wenhui Zhou, and Ercan Engin Kuruoglu, Unsupervised Learning of Light Field Depth Estimation with Spatial and Angular Consistencies. Neurocomputing, 2022. 501. 113-122. [code] Lili Lin, Hong Chen, Ercan Engin Kuruoglu, and Wenhui Zhou, Robust Structural Similarity Index Measure for Images with non-Gaussian Distortions. Pattern Recognition Letters, 2022. 163: 10-16. Lili Lin, Wan Luo, Zhengmao Yan, and Wenhui Zhou, Rigid-Aware Self-Supervised GAN for Camera Ego-Motion Estimation. Digital Signal Processing, 2022. 126: 103471. [code] Wenhui Zhou, Jiangwei Shi, Yongjie Hong, Lili Lin, and Ercan Engin Kuruoglu, Robust Dense Light Field Reconstruction from Sparse Noisy Sampling. Signal Processing, 2021. 186: 108121. [code][code2][MP4] Lili Lin, Weisheng Wang, Wan Luo, Lesheng Song, and Wenhui Zhou, Unsupervised Monocular Visual Odometry with Decoupled Camera Pose Estimation. Digital Signal Processing, 2021. 114: 103052.
Wenhui Zhou, Enci Zhou, Gaoming Liu, Lili Lin, Andrew Lumsdaine. Unsupervised Monocular Depth Estimation from Light Field Image, IEEE Transactions on Image Processing, 2020, 29: 1606-1617. [code] Wenhui Zhou, Gaomin Liu, Jiangwei Shi, Hua Zhang, Guojun Dai. Depth-guided View Synthesis for Light Field Reconstruction from a Single Image, Image and Vision Computing, 2020, 95: 0-103874. Wenhui Zhou, Xing Tao, Zhan Wei, Lili Lin. Automatic Segmentation of 3D Prostate MR Images with Iterative Localization Refinement, Digital Signal Processing, 2020, 98: 0-102649. Wenhui Zhou, Xingming Wei, Yuxiang Yan, Weisheng Wang, Lili Lin. A Hybrid Learning of Multimodal Cues for Light Field Depth Estimation, Digital Signal Processing, 2019, 95: 0-102585.
Selected Conference Papers： Jian Zheng, Shengwei Sang, Yifei Lu, Guojun Dai, Xiaoyang Mao, Wenhui Zhou*. PG-VTON: Front-and-Back Garment Guided Panoramic Gaussian Virtual Try-On with Diffusion Modeling. 42nd Computer Graphics International (CGI), Published in Computer Animation and Virtual Worlds (CAVW) journal. July 14-18, 2025. Hong Kong, China. [Male1, Male2, Male3, Female1, Female2] Hao Zhang, Junle Yu, Chenyu Wu, Jiahan Meng, Wenhui Zhou*. LF-SAET: Cascaded Spatial-Angular-EPI Transformers for Light Field Image Super-Resolution. 7th Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Xinjiang, China. 2024. 525--538. Fanding Huang, Zihao Yao, Wenhui Zhou*. DTBS: Dual-Teacher Bi-directional Self-training for Domain Adaptation in Nighttime Semantic Segmentation. 26th European Conference on Artificial Intelligence (ECAI). Kraków, Poland. 1084-1091, 2023 [code] Junle Yu, Luwei Ren, Wenhui Zhou*, Yu Zhang*, Lili Lin, Guojun Dai. PEAL: Prior-embedded Explicit Attention Learning for Robust Point Cloud Registration. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada. 2023. 17702-17711. [code]
Lin Zhong, Bangcheng Zong, Qiming Wang, Junle Yu, Wenhui Zhou*. Implicit Epipolar Geometric Function based Light Field Continuous Angular Representation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - 3rd Workshop on Light Fields for Computer Vision LFNAT: New Applications and Trends in Light Fields (LFNAT). Vancouver, Canada. 2023. [code is coming soon] Yu Zhang, Yu Junle, Xiaolin Huang, Wenhui Zhou, Ji Hou. PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry. European Conference on Computer Vision (ECCV). Tel Aviv, Israel. 2022. [code] Dizhi Ma, Andrew Lumsdaine, Wenhui Zhou. Flexible Spatial and Angular Light Field Super Resolution. The 27th IEEE International Conference on Image Processing (ICIP). Abu Dhabi. 2020. Xing Tao, Yuexiang Li, Wenhui Zhou, Kai Ma, Yefeng Zheng. Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI20). 2020. Wenhui Zhou, Enci Zhou, Yuxiang Yan, Lili Lin, and Andrew Lumsdaine. Learning Depth Cues from Focal Stack for Light Field Depth Estimation. The 26th IEEE International Conference on Image Processing (ICIP). Taipei. 2019. Wenhui Zhou, Linkai Liang, Hua Zhang, Andrew Lumsdaine, Lili Lin. Scale and Orientation Aware EPI-Patch Learning for Light Field Depth Estimation. 24th International Conference on Pattern Recognition (ICPR). Beijing, China. 2018, 2362-2367. Wenhui Zhou, Pengfei Li, Andrew Lumsdaine, Lili Lin. Light-Field Flow: A Subpixel-accuracy Depth Flow Estimation with Geometric Occlusion Model from a Single Light-Field Image. IEEE International Conference on Image Processing (ICIP). Beijing, China. 2017. Yaoxiang Luo, Wenhui Zhou, Junpeng Fang, Linkai Liang, Hua Zhang, Guojun Dai. EPI-Patch Based Convolutional Neural Network for Depth Estimation on 4D Light Field. International Conference on Neural Information Processing (ICONIP). 2017. Wenhui Zhou, Andrew Lumsdaine, Lili Lin. Depth Estimation with Cascade Occlusion Culling Filter for Light-field Cameras. 23rd International Conference on Pattern Recognition (ICPR). 2016.
Chinese Invention Patents
Wenhui Zhou, Yuhan Wang, Liangyan Mo, Wanzeng Kong, Guojun Dai. Temporal-Channel Cascaded Transformer for EEG Recognition. Chinese Invention Patent. Jul. 12, 2024. No: ZL202111614470.3. Wenhui Zhou, Hongfei Huang, Hua Zhang, Guojun Dai, Fengfan Xu, Ronghao Shen. A Detail Information Preserving Multi-view Depth Estimation Method. Chinese Invention Patent. Apr. 9, 2024. No: ZL202110151211.5. Zhan Wei, Wenhui Zhou, Hua Zhang, Hongfei Huang, Sixue Yang, Jiangwei Shi. A EEG Based Object Recognition Method. Chinese Invention Patent. Apr. 5, 2024. No: ZL202110172061.6. Wenhui Zhou, Yongjie Hong, Liangyan Mo, Hua Zhang, Guojun Dai. A Self-supervised Learning Method of Light Field Depth based on Iterative Occlusion Optimization. Chinese Invention Patent. Mar. 29, 2024. No: ZL202011151995.3. Wenhui Zhou, Weisheng Wang, Wei Sun, Hua Zhang, Guojun Dai. Unsupervised Monocular Visual Odometry with Decoupled Camera Pose Estimation. Chinese Invention Patent. Mar. 29, 2024. No: ZL202011151965.2. Wenhui Zhou, Yuxiang Yan, Yongjie Hong, Hua Zhang, Guojun Dai. A Unsupervised Deep Learning based Light Field Depth Estimation. Chinese Invention Patent. Jun. 20, 2023. No: ZL202010581570.X. Wenhui Zhou, Wei Sun, Wei Lang, Weisheng Wang, Zhengmao Yan, Hua Zhang, Yifan Wu, Guojun Dai. A Cascade Decoupled Pose Estimation. Chinese Invention Patent. Jul. 5, 2022. No: ZL202110725433.3. Wenhui Zhou, Linkai Liang, Xinming Wei, Enci Zhou. Scale and Orientation Aware Convolutional Neural Network for Light Field Depth Estimation. Chinese Invention Patent. Mar. 1, 2022. No: ZL201810317425.3. Wenhui Zhou, Pengfei Li, Linkai Liang, Xian Li, Yu Wang, Jiaqi Pan. A Depth Flow Estimation with Geometric Occlusion Model Light-field Camera. Chinese Invention Patent. Jul. 23, 2019. No: ZL201611262452.2. Wenhui Zhou, Jiaqi Pan, Pengfei Li. A Depth Estimation Method with Cascade Occlusion Culling Filter for Light-field Camera. Chinese Invention Patent. Dec. 25, 2018. No: ZL201610828210.9. Wenhui Zhou, Teng Song, Zhihai Sun, Yifan Wu, Chong Xu. A Simulated Retinal Filtering based Visual Saliency Detection Method. Chinese Invention Patent. Jul. 29, 2015. No: ZL201210560879.6. Wenhui Zhou, Teng Song, Zhihai Sun, Yifan Wu, Chong Xu. A Dual-Channel Color Contrast Fusion based Visual Saliency Detection. Chinese Invention Patent. Jun. 17, 2015. No: ZL201210497332.6. Wenhui Zhou, Teng Song, Zhihai Sun, Yifan Wu, Chong Xu. A Center-Surround Optimization Method for Visual Saliency Detection. Chinese Invention Patent. Apr. 22, 2015. No: ZL201210560401.3. Wenhui Zhou, Teng Song, Zhihai Sun, Hua Zhang, Xuehui Wei. A Visual Saliency Detection Method Based on the Fusion of Regional Color and HoG Features. Chinese Invention Patent. Apr. 22, 2015. No: ZL201210311804.4. Wenhui Zhou, Jin Jiang, Guojun Dai, Haoran Ren, Hua Zhang, Zhihai Sun, Xuehui Wei. Self-localization in 3D Dynamic Multimedia Sensor Network Based on Binocular Visual Nodes. Chinese Invention Patent. Mar. 5, 2014. No. ZL201110364395.X. Wenhui Zhou, Bin Lou, Hua Zhang, Zhihai Sun, Eryong Wu, Guojun Dai. A Discriminative Visual Saliency Detection Method Based on the Gradient Orientation Histogram. Chinese Invention Patent. Mar. 15, 2013. No. ZL201010524357.1. Wenhui Zhou, Bin Lou, Hua Zhang, Zhihai Sun, Eryong Wu, Guojun Dai. A Visual Saliency Detection Method Based on Weber Theorem and Center-Surround Hypothesis. Chinese Invention Patent. Sep. 19, 2012. No. ZL201110002235.0. Wenhui Zhou, Bin Lou, Zhihai Sun, Hua Zhang, Xuehui Wei, Guojun Dai. An Edge Preserving Adaptive Weighted Filtering Method for Natural Scene Image. Chinese Invention Patent. Oct. 3, 2012. No. ZL201110182918.9. Wenhui Zhou, Guangfei Liu. Binocular Video Synchronous Acquisition Device. Chinese Invention Patent. Oct. 5, 2011, No. ZL201010122968.3.
|
