Yuantong Zhang (张圆通)

Ph.D. Candidate in Photogrammetry and Remote Sensing

School of Remote Sensing and Information Engineering, Wuhan University

Email | Advisor: Zhenzhong Chen | Wuhan University

I am a Ph.D. candidate at the School of Remote Sensing and Information Engineering, Wuhan University, working in the Intelligent Information Processing Laboratory. My research focuses on video and image processing, with particular interests in video super-resolution, frame interpolation, low-light enhancement, and learned image or video compression.

Yuantong Zhang

Education

  • 2021 - Present: Ph.D. Candidate, Photogrammetry and Remote Sensing, Wuhan University
  • 2017 - 2021: B.Eng., Computer Science and Technology, Wuhan University

Research Interests

  • Video super-resolution
  • Video frame interpolation
  • Low-light image enhancement
  • Learned image compression
  • Video compression

Research and Project Experience

  • NTIRE 2026 Video Frame Interpolation Challenge: Technical lead of the first-place solution in both Track 1 and Track 2.
  • Space-Time Video Super-Resolution: Research on fixed-ratio, arbitrary-time, and continuous space-time video enhancement.
  • Image Preprocessing for Video Compression: Research and deployment for pre-processing methods in streaming and transcoding scenarios.
  • Video Enhancement for Live Streaming: Lightweight video super-resolution and low-light enhancement for live streaming applications.
  • Lightweight End-to-End Image Compression: Efficient learned image compression for extremely low bitrate scenarios and competition-level evaluation.

Publications

Journal Papers

  1. Yuantong Zhang, Hanyou Zheng, Daiqin Yang, Zhenzhong Chen, Haichuan Ma, Wenpeng Ding. Space-Time Video Super-resolution with Neural Operator. IEEE Transactions on Image Processing, 2025.
  2. Weijie Bao, Yuantong Zhang, Jianghao Jia, Zhenzhong Chen, Shan Liu. Joint Reference Frame Synthesis and Post Filter Enhancement for Versatile Video Coding. Journal of Visual Communication and Image Representation, 2025.
  3. Yuantong Zhang, Baoxin Teng, Daiqin Yang, Zhenzhong Chen, Haichuan Ma, Gang Li, Wenpeng Ding. Learning a Single Convolutional Layer Model for Low Light Image Enhancement. IEEE Transactions on Circuits and Systems for Video Technology, 34(7): 5995-6008, 2024.
  4. Yuantong Zhang, Daiqin Yang, Zhenzhong Chen, Wenpeng Ding. Continuous Space-Time Video Super-Resolution with Multi-stage Motion Information Reorganization. ACM Transactions on Multimedia Computing, Communications, and Applications, 2024.
  5. Jianghao Jia, Yuantong Zhang, Han Zhu, Zhenzhong Chen, Zizheng Liu, Xiaozhong Xu, Shan Liu. Deep Reference Frame Generation Method for VVC Inter Prediction Enhancement. IEEE Transactions on Circuits and Systems for Video Technology, 34(5): 3111-3124, 2024.
  6. Jie Yang, Yuantong Zhang, Zhenzhong Chen, Daiqin Yang. An Illumination-Guided Dual-Domain Network for Image Exposure Correction. Journal of Visual Communication and Image Representation, 2024.
  7. Yuantong Zhang, Huairui Wang, Han Zhu, Zhenzhong Chen. Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolution. IEEE Transactions on Circuits and Systems for Video Technology, 33(5): 2116-2128, 2023.

Conference Papers

  1. Yuantong Zhang, Zhenzhong Chen. Continuous Space-Time Video Resampling with Invertible Motion Steganography. CVPR, 2025.
  2. Chengzhuo Gui, Yuantong Zhang, Weijie Bao, Zhenzhong Chen, Huairui Wang, Shan Liu. Deep Reference Frame for Versatile Video Coding with Structural Re-parameterization. VCIP, 2024.
  3. Yifei Long, Yuantong Zhang, Daiqin Yang, Zhenzhong Chen, Huairui Wang, Shan Liu. Lightweight Arbitrary-Scale Super-Resolution of Remote Sensing Images via Super-Scale Feature. VCIP, 2024.
  4. Yuantong Zhang, Nianxiang Fu, Guo Yu, Xiangdong Lv, Huairui Wang, Zhenzhong Chen. Learned Image Compression with Enhanced Dynamic Spatial Aggregation and Asymmetric Entropy Model. VCIP, 2023.
  5. Jie Yang, Yuantong Zhang, Daiqin Yang, Zhenzhong Chen. An Efficient Method for Real-Time Image Exposure Correction. VCIP, 2023.
  6. Wenhui Meng, Yuantong Zhang, Jianghao Jia, Songtao Chao, Zhenzhong Chen. Towards Lightweight Deep Reference Frame for Versatile Video Coding. VCIP, 2023.
  7. Yuantong Zhang, Huairui Wang, Zhenzhong Chen. Controllable Space-Time Video Super-Resolution via Enhanced Bidirectional Flow Warping. VCIP, 2022.

Awards and Honors

  • 2026: First Prize of Wang Zhizhuo Innovation Talent Award (王之卓创新人才一等奖)
  • 2026: First Place in High FPS Video Frame Interpolation Track 1 and Track 2, CVPR Workshop
  • 2026: Second Place in Real-World Mobile Super-Resolution, CVPR Workshop
  • First Prize in the "AI + Image Coding" Track, 5th National Artificial Intelligence Competition (第五届全国人工智能大赛 “AI+图像编码”赛道一等奖，第一名)
  • 2023 - 2024: Lei Jun Scholarship (雷军腾飞奖学金)
  • 2023 - 2024: First-Class Excellent Academic Scholarship (一等优秀学业奖学金)
  • 2022 - 2023: Lei Jun Scholarship (雷军腾飞奖学金)
  • 2022: Advanced Individual in the China Graduate Innovation Practice Series Competition (中国研究生创新实践系列大赛先进个人)
  • 2021 - 2022: First-Class Excellent Academic Scholarship (一等优秀学业奖学金)
  • 2021: Second Prize, China Graduate Mathematical Contest in Modeling (研究生数学建模大赛二等奖)

Standards and Technical Contributions

  • Weijie Bao, Yucong Cai, Yuantong Zhang, Zhenzhong Chen. AHG14: The Extension of SADL Library, JVET-AF0236 (采纳).
  • Ding Ding, Xiaozhong Xu, Shan Liu, Han Zhu, Yuantong Zhang, Huairui Wang, Zhenzhong Chen. Learning-based Image Compression Response to the JPEG AI Call for Proposals, ISO/IEC JTC 1/SC29/WG1 M96051.
  • Ding Ding, Xiaozhong Xu, Shan Liu, Han Zhu, Yuantong Zhang, Huairui Wang, Zhenzhong Chen. Task-driven End-to-End Image Compression Response to the JPEG AI Call for Proposals, ISO/IEC JTC 1/SC29/WG1 M96050.
  • Jianghao Jia, Yuantong Zhang, Han Zhu, Zhenzhong Chen, Zizheng Liu, Liqiang Wang, Xiaozhong Xu, Shan Liu. AHG11: Deep Reference Frame Generation for Inter Prediction Enhancement, JVET-AB0114.
  • Jianghao Jia, Yuantong Zhang, Han Zhu, Zhenzhong Chen, Zizheng Liu, Xiaozhong Xu, Shan Liu. AHG11: Deep Reference Frame Generation for Inter Prediction Enhancement, JVET-AC0114.
  • Jianghao Jia, Yuantong Zhang, Han Zhu, Zhenzhong Chen, Zizheng Liu, Xiaozhong Xu, Shan Liu. EE1-2.1: Deep Reference Frame Generation for Inter Prediction Enhancement, JVET-AD0160.
  • Weijie Bao, Wenhui Meng, Jianghao Jia, Yuantong Zhang, Huairui Wang, Zhenzhong Chen, Zizheng Liu, Xiaozhong Xu, Shan Liu. EE1-5.1: Deep Reference Frame Generation for Inter Prediction Enhancement, JVET-AE0112.
  • Weijie Bao, Xin Chen, Jianghao Jia, Yuantong Zhang, Zhenzhong Chen, Zizheng Liu, Xiaozhong Xu, Shan Liu. EE1-2.1: Deep Reference Frame Generation for Inter Prediction Enhancement, JVET-AF0208.

Patents

  • A Real-Time Pedestrian Detection Method Using Background Modeling for Data Enhancement (一种利用背景建模增强数据的实时行人检测方法)