Academic Areas: ComputerVision, Pattern Recognition, Machine Learning
Research Interests:Monocular Depth Prediction, Image Registration, Object Counting, Image Aesthetics (image cropping, bokeh, etc.), Point Cloud Processing
Zhiguo Cao is a professor of the Department of Intelligent Science and Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology. He has been appointed the director of the academic committee of the School of Artificial Intelligence and Automation since 2018
Professor Cao’s research interest involves Monocular Depth Prediction, Image Registration, Object Counting, Image Aesthetics (image cropping, bokeh, etc.), Point Cloud Processing and so on. During his whole career life, he focuses on designing the practical computer vision system to balance the theoretical research and engineering applications. A number of his research achievements have been successfully applied to the industrial fields. Meanwhile, he also addresses the efforts to boost the cutting-edge inter-discipline research among computer vision, machine learning,consumer cloud services, agriculture, meteorology and medicine.
Academic Degree:
Sept. 1981 – July. 1985, University of Electronic Science and Technology of China, B. S. in Electronic Engineering
Sept. 1987 – Apr. 1990, University of Electronic Science and Technology of China, M. S. in Telecommunication and Electronic system
Sept. 1996 – Dec. 2001, Huazhong University of Science and Technology, Ph. D. in Pattern Recognition and Intelligent System
Professional Experience:
Apr. 2004 – Present: Professor, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology
May 1998 – Apr. 2004: Associate Professor, Institute of Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology
Jan. 1995 – Apr. 1998: Assistant Professor, Institute of Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology
Apr. 1990 – Dec. 1994: Assistant Professor, Department of Electronic and Information Engineering, Huazhong University of Science and Technology
Jul. 1985 – Aug. 1987: Assistant Engineer, Design Institute of Wuhan Telecommunication Factory
Selected Publications:
1. Xianrui Luo, Zijin Wu, Juewen Peng, Huiqiang Sun,Zhiguo Cao*and Guosheng Lin,“Dual-Camera All-in-Focus Neural Radiance Fields”,IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), (Early Access), DOI: 10.1109/TPAMI.2025.3537178
2. Juewen Peng,Zhiguo Cao*, Xianrui Luo, Ke Xian, Wenfeng Tang, Jianming Zhang and Guosheng Lin,“BokehMe++: Harmonious Fusion of Classical and Neural Rendering for Versatile Bokeh Creation”,IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI),Vol.47, No.3: 1530-1547, March 2025, DOI: 10.1109/TPAMI.2024.3501739
3. Hao Lu, Wenze Liu, Hongtao Fu,Zhiguo Cao*, “FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures”,International Journal of Computer Vision (IJCV), Vol.133, No.1: 151-172, Jan. 2025, DOI: 10.1007/s11263-024-02191-8
4. Yiran Wang, Min Shi, Jiaqi Li, Chaoyi Hong, Zihao Huang, Juewen Peng,Zhiguo Cao, Jianming Zhang, Ke Xian, and Guosheng Lin，“NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation”,IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), Vol.47, No.1: 583-600, Jan. 2025, DOI: 10.1109/TPAMI.2024.3476387
5. Jiaqi Li, Yiran Wang, Jinghong Zheng, Zihao Huang, Ke Xian,Zhiguo Cao, Jianming Zhang,“Self-Distilled Depth Refinement with Noisy Poisson Fusion”,The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS2024), Dec.10-15, Vancouver, Canada
6. Xianrui Luo, Huiqiang Sun, Juewen Peng, andZhiguo Cao*,“Dynamic Neural Radiance Field from Defocused Monocular Video”,The 18th European Conference of Computer Vision (ECCV2024), Proceedings, Part V，LNCS15063：142-159，September 29–October 4, 2024, Milan, Italy,DOI：https://doi.org/10.1007/978-3-031-72652-1_9
7. Liao Shen, Tianqi Liu, Huiqiang Sun, Xinyi Ye, Baopu Li, Jianming Zhang, andZhiguo Cao*,“DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion”，The 18th European Conference of Computer Vision (ECCV2024), Proceedings, Part XV，LNCS15073：336-353, September 29–October 4, 2024, Milan, Italy,DOI：https://doi.org/10.1007/978-3-031-72633-0_19
8. Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang,Zhiguo Cao*, Wei Li, and Ziwei Liu,“MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo”,The 18th European Conference of Computer Vision (ECCV2024)Proceedings, Part XVIII，LNCS15076：37-53, September 29–October 4, 2024, Milan, Italy,DOI：https://doi.org/10.1007/978-3-031-72649-1_3
9. Tingbing Yan, Wenzheng Zeng, Yang Xiao, Xingyu Tong, Bo Tan, Zhiwen Fang,Zhiguo Cao, and Joey Tianyi Zhou，“CrossGLG: LLM Guides One-Shot Skeleton-Based 3D Action Recognition in a Cross-Level Manner”,The18th European Conference of Computer Vision (ECCV2024)Proceedings, Part XX，LNCS15078：113-131，September 29–October 4, 2024, Milan, Italy, DOI：https://doi.org/10.1007/978-3-031-72661-3 7
10. Yizheng Wu, Zhiyu Pan, Kewei Wang, Xingyi Li, Jiahao Cui, Liwen Xiao, Guosheng Lin, andZhiguo Cao,“Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation”,IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), Vol.46, No.12: 9567-9582，Dec.2024, DOI: 10.1109/TPAMI.2024.3424243
11. Ke Xian,Zhiguo Cao, Chunhua Shen, Guosheng Lin,“Towards Robust Monocular Depth Estimation: A New Baseline and Benchmark”,International Journal of Computer Vision(IJCV),Vol.132, No.7: 2401-2419, 2024, DOI: 10.1007/s11263-023-01979-4
12. Tianqi Liu, Xinyi Ye, Min Shi, Zihao Huang, Zhiyu Pan, Zhan Peng,Zhiguo Cao*,“Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 7654-7663, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.00731
13. Huiqiang Sun, Xingyi Li, Liao Shen, Xinyi Ye, Ke Xian,Zhiguo Cao*,“DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 7517-7527, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.00718
14. Zhan Peng, Xinyi Ye, Weiyue Zhao, Tianqi Liu, Huiqiang Sun, Baopu Li,Zhiguo Cao*,“3D Multi-frame Fusion for Video Stabilization”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 7507-7516, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.00717
15. Xingyi Li,Zhiguo Cao, Yizheng Wu, Kewei Wang, Ke Xian, Zhe Wang, Guosheng Lin,“S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 20102-20112, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.01900
16. He Guo, Zixuan Ye,Zhiguo Cao, Hao Lu,“In-Context Matting”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 3711-3720, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.00356
17. Zixuan Ye, Wenze Liu, He Guo, Yujia Liang, Chaoyi Hong, Hao Lu,Zhiguo Cao,“Unifying Automatic and Interactive Matting with Pretrained ViTs”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 25585-25594, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.02417
18. Kewei Wang, Yizheng Wu, Jun CEN, Zhiyu Pan, Xingyi Li, Zhe Wang,Zhiguo Cao, Guosheng Lin.“Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations”,The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024), 14638-14647, Jun 17th-21st, 2024, Seattle, USA, DOI: 10.1109/CVPR52733.2024.01387
19. Yiran Wang, Min Shi, Jiaqi Li, Zihao Huang,Zhiguo Cao*, Jianming Zhang, Ke Xian, Guosheng Lin,“Neural Video Depth Stabilizer”,International Conference on Computer Vision (ICCV2023), 9432-9442, October 2—6, 2023, Paris, France,DOI：10.1109/ICCV51070.2023.00868
20. Xinyi Ye, Weiyue Zhao, Tianqi Liu, Zihao Huang,Zhiguo Cao*, Xin Li,“Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells”,International Conference on Computer Vision (ICCV2023), 9432-9442, October2—6, 2023, Paris, France, DOI: 10.1109/ICCV51070.2023.01619
21. Chengxin Liu, Hao Lu,Zhiguo Cao*, Tongliang Liu,“Point-Query Quadtree for Crowd Counting, Localization, and More”,International Conference on Computer Vision (ICCV2023), 9432-9442, October 2—6, 2023, Paris, France, DOI: 10.1109/ICCV51070.2023.00161
22. Weiyue Zhao, Xin Li, Zhan Peng, Xianrui Luo, Xinyi Ye, Hao Lu,Zhiguo Cao*,“Fast Full-frame Video Stabilization with Iterative Optimization”,International Conference on Computer Vision (ICCV2023), 9432-9442, October 2—6, 2023, Paris, France, DOI: 10.1109/ICCV51070.2023.02151
23. Wenze Liu, Hao Lu, Hongtao Fu,Zhiguo Cao,“Learning to Upsample by Learning to Sample”,International Conference on Computer Vision (ICCV2023), 9432-9442, October 2—6, 2023, Paris, France, DOI: 10.1109/ICCV51070.2023.00554
24. Tianqi Liu, Xinyi Ye, Weiyue Zhao, Zhiyu Pan, Min Shi,Zhiguo Cao*,“When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo”,International Conference on Computer Vision (ICCV2023), 9432-9442, October 2—6, 2023, Paris, France, DOI: 10.1109/ICCV51070.2023.01658
25. Weiyue Zhao, Hao Lu, Xinyi Ye,Zhiguo Cao*, Xin Li,“Learning Probabilistic Coordinate Fields for Robust Correspondences”,IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), Vol.45, No.10: 12004-12021, October, 2023, DOI: 10.1109/TPAMI.2023.3284487
26. Weiyue Zhao, Hao Lu,Zhiguo Cao*, Xin Li,“A2B: Anchor to Barycentric Coordinate for Robust Correspondence”,International Journal of Computer Vision(IJCV), Vol.131, No.10: 2582-2606, Oct. 2023, DOI: 10.1007/s11263-023-01827-5
27. Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Chunhua Shen,Zhiguo Cao*,“From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting”,International Journal of Computer Vision(IJCV), Vol. 131: 1722–1740, July, 2023, DOI: 10.1007/s11263-023-01782-1
28. Xingyi Li,Zhiguo Cao, Huiqiang Sun, Jianming Zhang, Ke Xian, Guosheng Lin,“3D Cinemagraphy from a Single Image”,IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2023), 4595-4605, June 18-22, 2023, Vancouver, Canada, DOI: 10.1109/CVPR52729.2023.00446
29. Changlong Jiang, Yang Xiao, Cunlin Wu, Mingyang Zhang, Jinghong Zheng,Zhiguo Cao, Joey Tianyi Zhou,“A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image”,IEEE/CVF Conference on ComputerVision and Pattern Recognition (CVPR2023), 4595-4605, June 18-22, 2023, Vancouver, Canada,DOI：10.1109/CVPR52729.2023.00854
30. Wenzheng Zeng, Yang Xiao, Sicheng Wei, Jin Fan Gan, Xintao Zhang,Zhiguo Cao, Zhiwen Fang, Joey Tianyi Zhou,“Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video”,IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2023), 4595-4605, June 18-22, 2023, Vancouver, Canada,DOI：10.1109/CVPR52729.2023.01331
31. Min Shi, Zihao Huang, Xianzheng Ma, Xiaowei Hu,Zhiguo Cao,“Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation”,IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2023), 4595-4605, June 18-22, 2023, Vancouver, Canada,DOI：10.1109/CVPR52729.2023.00706
32. Juewen Peng, Jianming Zhang, Xianrui Luo, Hao Lu, Ke Xian,Zhiguo Cao,“MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects”,European Conference on Computer Vision (ECCV2022), 590-607, October 23-27, Tel Aviv, Israel.DOI: 10.1007/978-3-031-20068-7 34.
33. Yizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu,Zhiguo Cao*, Weicai Zhong,“3D Instances as 1D Kernels”,European Conference on Computer Vision (ECCV2022), 234-252, October 23-27, Tel Aviv, Israel, DOI: 10.1007/978-3-031-19818-2 14.
34. Chengxin Liu, Kewei Wang, Hao Lu,Zhiguo Cao*, Ziming Zhang,“Robust Object Detection With Inaccurate Bounding Boxes”,European Conference on Computer Vision (ECCV2022),53-68, Oct.23-27, 2022, Tel Aviv, Israel, 10.1007/978-3-031-20080-9 4.
35. Juewen Peng,Zhiguo Cao, Xianrui Luo, Hao Lu, Ke Xian, and Jianming Zhang,“BokehMe: When Neural Rendering Meets Classical Rendering”,IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2022), 16283-16292, Jun. 19—24, 2022, New Orleans,USA,DOI：10.1109/CVPR52688.2022.01580
36. Min Shi, Hao Lu, Chen Feng, Chengxin Liu,Zhiguo Cao*,“Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting”,IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2022), 9529-9538, Jun. 19—24, 2022, NewOrleans, USA, DOI: 10.1109/CVPR52688.2022.00931
Awards and Honors:
1. As Weiyue Zhao's advisor, I supervised his master's thesis, which was awarded the 2024 Best Master's Thesis Award by the China Society of Image and Graphics.
2. The Winner Award in “Monocular Depth from Images of Specular and Transparent Surfaces Challenge” in TRYCKY 2024 conjunction with ECCV 2024.
3. The Winner Award in “NTIRE 2024 HR Depth from Images of Specular and Transparent Surfaces Challenge – Track 2 Mono” in conjunction with CVPR 2024.
4. As Juewen Peng's advisor, I supervised his master's thesis, which was awarded the 2024 Best Master's Thesis Award by the Chinese Association Automation.
5. The Winner Award in “NTIRE 2023 Challenge on Lens-to-Lens Bokeh Effect Transformation” in conjunction with CVPR 2023.
6. As the instructor, the team won the highest award at the 18th "Challenge Cup" National College Student Extracurricular Academic and Technological Works Competition in 2022.
7. The second place in “Global Wheat Challenge 2021” in conjunction with ICCV 2021.
8. The Runner-Up Award in “MAI 2021 Single-Image Depth Estimation Challenge”, “Mobile AI Woekshop and Challenge 2021” in conjunction with CVPR 2021.
9. The Runner-Up Award in “AIM 2020 Challenge on Rendering Realistic Bokeh”, “Advances in image manipulation workshop” in conjunction with ECCV2020.
10. The second place in the task “Mono Depth Estimation”, “Robust Vision Challenge 2020” in conjunction with ECCV 2020.
11. Runner-up of the “Depth-based 3D Hand Pose Estimation” Task, the 2019 Hands Challenge on 3D hand pose estimation in conjunction with HANDS 2019 workshop, ICCV2019.
12. The Best Poster Award, ”A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image”, 5th workshop on Observing and Understanding hands in Action in conjunction with ICCV2019.
13. The outstanding paper awards, “In-field automatic observation of wheat heading stage using computer vision”, European Society of Agricultural Engineers, 2018
14. The Best Paper award, "Real-Time Stereo Matching System", 11th International Conference on Intelligent Robotics and Applications, ICIRA 2018.
15. The second prize in the task “Single Image Depth Prediction”, “Robust Vision Challenge” in conjunction with CVPR 2018.
Course Taught:
For Undergraduates:Pattern Recognition and Machine Learning
For Graduates:Pattern Recognition and Probabilistic Machine Learning
