ZHANG Pingping
About Me
I received my Ph.D. degree in Computer Science from City University of Hong Kong in June 2025, under the supervision of Prof. KWONG Tak Wu Sam and Prof. Shiqi Wang. My research interests lie at the intersection of data compression, image and video processing, and emerging AI techniques including AIGC, LLMs and MLLMs. My recent work is dedicated to improving the efficiency and applicability of vision-language and multimodal large language models (LVLMs/MLLMs).
Research Interests
- Data Compression: Deep image compression, deep video coding, point cloud compression
- AIGC: Multimodal representation learning, diffusion models
- LLM/LVLM/MLLMs: Inference acceleration, semantic-aware compression, AI agents
- Image Enhancement: Restoration and low-light image enhancement
News
- [Feb. 2025] Our paper about image compression is accepted to ICLR 2025.
- [Dec. 2024] Our paper about low-light image enhancement is accepted to TPAMI.
- [Jul. 2024] Our paper about 3DGS compression is accepted to ACM MM 2024.
- [Jun. 2024] Our paper about image compression is accepted to IEEE Transactions on Multimedia.
Selected Publications
LLM/VLM/MLLM/AIGC
- Under review: Pingping Zhang et al., "When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding" [Paper]
- Under review: Kecheng Chen, Pingping Zhang et al., "Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need" [Paper]
- ICLR 2025: Kecheng Chen, Pingping Zhang et al., "Test-time Adaptation for Image Compression with Distribution Regularization" [Paper]
Image/Video/Point Cloud Compression
- TMM 2024: Pingping Zhang, et al., "HNR-ISC: Hybrid Neural Representation for Image Set Compression" [Paper]
- ToMM 2024: Yuyu Xu, Pingping Zhang et al., "RGB-D Data Compression via Bi-Directional Cross-Modal Prior Transfer and Enhanced Entropy Modeling" [Paper] [Code]
- TCSVT 2023: Pingping Zhang, et al., "Rethinking semantic image compression: Scalable representation with cross-modality transfer" [Paper] [Code]
- ATSIPA 2024: Pingping Zhang, et al., "2D Gaussian Splatting for Image Compression" [Paper] [Code]
- TCSVT 2023: Jiancong Chen, Meng Wang, Pingping Zhang et al., "Sparse-to-Dense: High Efficiency Rate Control for End-to-end Scale-Adaptive Video Coding" [Paper]
- Neurocomputing 2023: Rongqun Lin, Meng Wang, Pingping Zhang et al., "Multiple Hypotheses Based Motion Compensation for Learned Video Compression" [Paper]
- ACMMM 2024: Xiangrui Liu, Xinju Wu, Pingping Zhang et al., "CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting" [Paper] [Code]
- TCSVT 2024: Xinju Wu, Pingping Zhang, et al., "Geometric Prior Based Deep Human Point Cloud Geometry Compression" [Paper]
Image Enhancement
- TPAMI 2024: Wenhui Wu, Jian Weng, Pingping Zhang et al., "Interpretable Optimization-Inspired Unfolding Network for Low-light Image Enhancement" [Paper] [Code]
- TCSVT 2021: Pingping Zhang, et al., "Progressive point cloud upsampling via differentiable rendering" [Paper] [Code]
- CVPR 2022: Wenhui Wu, Jian Weng, Pingping Zhang et al., "URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement" [Paper] [Code]
Services
Conference Reviewers
NeurIPS ICCV CVPR ACM Multimedia
Journal Reviewers
IEEE Transactions on Image Processing IEEE Transactions on Neural Networks and Learning Systems IEEE Transactions on Multimedia IEEE Transactions on Circuits and Systems for Video Technology APSIPA Transactions on Signal and Information Processing
Paper survey
Awards
Outstanding academic performance award, City University of Hong Kong, 2023 Research tuition scholarship, City University of Hong Kong, 2022, 2023