|
SHENG, Xihua 盛锡华
♦ Dr. Xihua Sheng is currently a Research Assistant Professor in the Department of Computing at The Hong Kong Polytechnic University (PolyU), where he is advised by Prof. Changwen Chen.
Email-1 xihua.sheng@polyu.edu.hk |
|
News
♦ 2026/02/26 is the last day in City University of Hong Kong. |
Publications♦ My research interests include image/video/point cloud coding and processing. |
|
CADC: Content Adaptive Diffusion-Based Generative Image Compression
Xihua Sheng, Lingyu Zhu, Tianyu Zhang, Dong Liu, Shiqi Wang, Jing Wang The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2026 |
|
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision
Xihua Sheng, Li Li, Dong Liu, Houqiang Li, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 |
|
Prediction and Reference Quality Adaptation for Learned Video Compression
Xihua Sheng, Li Li, Dong Liu, Houqiang Li, IEEE Transactions on Image Processing (TIP), 2025 |
|
Attribute Artifacts Removal for Geometry-Based Point Cloud Compression
Xihua Sheng, Li Li, Dong Liu, Zhiwei Xiong, IEEE Transactions on Image Processing (TIP), 2022 |
|
Fine-Grained Motion Compression and Selective Temporal Fusion for Neural B-Frame Video Coding
Xihua Sheng, Peilin Chen, Meng Wang, Li Zhang, Shiqi Wang, Dapeng Oliver Wu IEEE Transactions on Multimedia (TMM), 2026 |
|
Bi-Directional Deep Contextual Video Compression
Xihua Sheng, Li Li, Dong Liu, Shiqi Wang IEEE Transactions on Multimedia (TMM), 2025 |
|
Temporal Context Mining for Learned Video Compression
Xihua Sheng, Jiahao Li, Bin Li, Li Li, Dong Liu, Yan Lu IEEE Transactions on Multimedia (TMM), 2022 |
|
Deep-PCAC: An End-to-End Deep Lossy Compression Framework for Point Cloud Attributes
Xihua Sheng, Li Li, Dong Liu, Zhiwei Xiong, Zhu Li, Feng Wu IEEE Transactions on Multimedia (TMM), 2021 |
|
Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression
Xihua Sheng, Li Li, Dong Liu, Houqiang Li IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024 |
|
DRFC: An End-to-End Deep Dynamic RF Signal Compression Framework
Xihua Sheng, Peilin Chen, Shiqi Wang, Dapeng Oliver Wu IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025 |
Adopted Proposals♦ I serve as a software coordinator of AVS End-to-End Video Coding Exploration Model. |
|
AVS End-to-End Video Coding Reference Model EEM-v0.1.
AVS Proposal No. M7995. Xihua Sheng, Li Li, Dong Liu Submitting Institution: University of Science and Technology of China (USTC). Meeting Location: Lichuan, Hubei. Meeting Date: August 21-27, 2023. |
|
Impact of Varying Simulated Quantization Uniform Noise Amplitude on Coding Performance in AVS-EEM-v0.1.
AVS Proposal No. M8002. Xihua Sheng, Li Li, Dong Liu Submitting Institution: University of Science and Technology of China (USTC). Meeting Location: Lichuan, Hubei. Meeting Date: August 21-27, 2023. |
|
Impact of Increasing Training Iterations on Coding Performance in AVS-EEM-v0.1.
AVS Proposal No. M8003. Xihua Sheng, Li Li, Dong Liu Submitting Institution: University of Science and Technology of China (USTC). Meeting Location: Lichuan, Hubei. Meeting Date: August 21-27, 2023. |
|
A Feature-Based Motion Prediction Technique for End-to-End Video Coding.
AVS Proposal No. M8004. Xihua Sheng, Li Li, Dong Liu Submitting Institution: University of Science and Technology of China (USTC). Meeting Location: Lichuan, Hubei. Meeting Date: August 21-27, 2023. |
|
Multi-Scale Temporal Context Prediction for EEM.
AVS Proposal No. M8098. Xihua Sheng, Li Li, Dong Liu Submitting Institution: University of Science and Technology of China (USTC). Meeting Location: Chengdu, Sichuan. Meeting Date: December 13-16, 2023. |
|
YUV-Trained I-Frame Model for EEM.
AVS Proposal No. M8328. Xihua Sheng, Li Li, Dong Liu Submitting Institution: University of Science and Technology of China (USTC). Meeting Location: Shaoxing, Zhejiang. Meeting Date: June 20-23, 2024. |
|
Reference Quality Adaptation Method for EEM.
AVS Proposal No. M8624. Xihua Sheng, Shiqi Wang, Li Li, Dong Liu Submitting Institution: City University of Hong Kong (CityU), University of Science and Technology of China (USTC). Meeting Location: Zhuhai, Guangdong. Meeting Date: December 18-21, 2024. |
|
EEM I-Frame Model with Extended Bitrate Range.
AVS Proposal No. M8794. Xihua Sheng, Shiqi Wang, Li Li, Dong Liu Submitting Institution: City University of Hong Kong (CityU), University of Science and Technology of China (USTC). Meeting Location: Changsha, Hunan. Meeting Date: March 12-15, 2025. |
|
A Simplified EEM Motion Estimation Technique Based on Adaptive Downsampling.
AVS Proposal No. M9162. Xihua Sheng, Shiqi Wang, Long Xu, Zhirui Zuo, Li Li, Dong Liu Submitting Institution: City University of Hong Kong (CityU), University of Science and Technology of China (USTC). Meeting Location: Dalian, Liaoning. Meeting Date: August 23-26, 2025. |
|
Enhanced Training Dataset and Method for EEM.
AVS Proposal No. M9351. Xihua Sheng, Shiqi Wang, Zhirui Zuo, Li Li, Dong Liu Submitting Institution: City University of Hong Kong (CityU), University of Science and Technology of China (USTC). Meeting Location: Macau. Meeting Date: December 6-9, 2025. |
|
A Feature Refresh Method for Enhanced Training of EEM.
AVS Proposal No. M9352. Xihua Sheng, Shiqi Wang, Zhirui Zuo, Li Li, Dong Liu Submitting Institution: City University of Hong Kong (CityU), University of Science and Technology of China (USTC). Meeting Location: Macau. Meeting Date: December 6-9, 2025. |
Grand Challenges
♦ Top Performance Award in the End-to-end Track of ISCAS 2023 Grand Challenge on Neural Network-based Video Coding |
Awards
♦ 2025 ACM China SIGMM Award for Outstanding PhD Thesis |
|
|