Bolin Chen — Homepage

About

I received my Ph.D. in Computer Science from City University of Hong Kong in February 2025. In March 2025, I joined Alibaba DAMO Academy as a Senior Algorithm Engineer and started a Joint Postdoctoral Fellow at Fudan University.

My Ph.D. research centered on video coding and standardization, resulting in 30+ publications and 50+ technical MPEG/JVET proposals. Since then, my research has broadened to frontier 3D vision and its practical deployment.

Research Interests

3D Vision Research and Productization. 3D reconstruction, generation, and deployment.
Generative Visual Compression. Compression for image, video, and visual content with generative methods.
Ultra-Low-Bitrate Avatar Coding. Efficient representation of talking faces and human avatars.
Perception-aware Visual Computing. Perceptual quality assessment, human-centric image/video processing, and generative media detection.

Publications

30+ peer-reviewed papers. 📄 Full Paper List →
Selected published papers are listed below.

First-Author Papers

Standardizing Generative Face Video Compression using Supplemental Enhancement Information B. Chen, Y. Ye, J. Chen, R. Liao, S. Yin, S. Wang, K. Yang, Y. Li, Y. Xu, Y.-K. Wang, S. Gehlot, G.M. Su, P. Yin, S. McCarthy, G.J. Sullivan. IEEE Transactions on Multimedia CCF-A
Interactive Face Video Coding: A Generative Compression Framework B. Chen, Z. Wang, B. Li, S. Wang, S. Wang, Y. Ye. IEEE Transactions on Image Processing CCF-A
Compact Temporal Trajectory Representation for Talking Face Video Compression B. Chen, Z. Wang, B. Li, S. Wang, Y. Ye. IEEE Transactions on Circuits and Systems for Video Technology CCF-B
Beyond keypoint coding: Temporal evolution inference with compact feature representation for talking face video compression B. Chen, Z. Wang, B. Li, R. Lin, S. Wang, Y. Ye. IEEE Data Compression Conference (DCC) CCF-B Oral
Multipath feature recalibration DenseNet for image classification B. Chen, T. Zhao, J. Liu, L. Lin. International Journal of Machine Learning and Cybernetics SCI
Generative Face Video Coding Techniques and Standardization Efforts: A Review B. Chen, J. Chen, S. Wang, Y. Ye. IEEE Data Compression Conference (DCC) CCF-B Oral, Capocelli Prize finalist
Generative Visual Compression: A Review B. Chen, S. Yin, P. Chen, S. Wang, Y. Ye. IEEE International Conference on Image Processing (ICIP) CCF-C Oral

Co-Author Papers

Ultra-Low Bitrate Face Video Compression Based on Conversions from 3D Keypoints to 2D Motion Map Z. Wang, B. Chen, S. Wang, S. Wang, Y. Ye, S. Ma. IEEE Transactions on Image Processing CCF-A
FTGID: Fine-grained Text-driven Framework for Universal Generative Image Detection Z. Huang, L. Lin, B. Chen, Y. Wang, T. Zhao. IEEE Transactions on Image Processing CCF-A
Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective Method Y. Li, B. Chen, B. Chen, M. Wang, S. Wang, W. Lin. IEEE Transactions on Multimedia CCF-A
ColorAssist: Perception-Based Recoloring for Color Vision Deficiency Compensation L. Lin, S. Xie, Y. Wang, B. Chen, Y. Xue, X. Zhuang, T. Zhao. IEEE Transactions on Image Processing CCF-A
DeepSVC: Deep Scalable Video Coding for Both Machine and Human Vision H. Lin, B. Chen, Z. Zhang, J. Lin, X. Wang, T. Zhao. ACM International Conference on Multimedia (ACM MM) CCF-A

50+ technical proposals contributed to JVET and MPEG. 📄 Full Proposal List →
Selected first-author adopted proposals are listed below.

First-Author Adopted Proposals

JVET-AQ0140 AHG9: A showcase for picture quality indication in EOI SEI message extension Adopted
MPEG m74027 [GSC] Dual-Phase Morton Spatial Sorting for Efficient Mapping of GS Attribute Parameters to 2D Pixel Space Adopted
JVET-AJ0207 AHG9/AHG16: Performance results and suggestions on generative face video SEI message Adopted, Working Draft
JVET-AJ0209 AHG9/AHG16: Performance results of generative face video SEI message on high-resolution sequences Adopted, CTC
JVET-AI0048 AhG16: Improving GFVC Performance with Diverse Training Data Adopted
JVET-AI0195 AhG9/16: Updates on GFVC common software tools and GFV SEI message Adopted
JVET-AH0110 AHG16: Scalable Representation and Layered Reconstruction for Generative Face Video Compression Adopted
JVET-AH0114 AHG16: Updated Common Software Tools for Generative Face Video Compression Adopted
JVET-AG0042 AHG16: Proposed Common Software Tools and Testing Conditions for Generative Face Video Compression Adopted

70+ pending US/CN/PCT patents (10+ granted). Selected granted patents are listed below.

Method and apparatuses for using face video generative compression SEI message. US12621492B2 Granted
SEI message for generative face video. US12621494B2 Granted
Method and apparatus for talking face video compression. US12470746B2 Granted
Model training method, video encoding method and decoding method. CN114897189B Granted
Video encoding method, decoding method, electronic device and storage medium. CN114979672B Granted
A face video encoding method, decoding method and apparatus. CN114401406B Granted
A face video encoding method, decoding method and apparatus. CN114422795B Granted
Face video encoding method, decoding method and apparatus. CN114205585B Granted
Keypoints based video compression. US12477120B2 Granted
A kind of leucocyte extraction and classification method based on improvement K-means and convolutional neural networks. CN110110807B Granted
An optimized segmentation method for ambiguous pixels based on improved FCN and DenseNet. CN112541926B Granted
An objective video quality evaluation method based on observable coding effect strength. CN111711816B Granted

Professional Services

Area Chair / Committee

IEEE International Symposium on Circuits and Systems (ISCAS)
2026 IEEE International Conference on Multimedia and Expo (ICME 2026)

Invited Talks

IEEE MMSP 2026 (Thematic School) — Exploration and Standardization of Generative Face Video Compression: From Compact Representation to Unified Syntax

Organized Activities

ICME 2026 Special Session — Advances in Next-Generation Video Coding
VCIP 2026 Special Session — Advances in Next-Generation Video Coding

Reviewer

IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Multimedia (TMM)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS)
Knowledge-Based Systems (KBS)
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
IEEE Data Compression Conference (DCC) 2024/2026
IEEE International Conference on Multimedia and Expo (ICME) 2023/2025
ACM Multimedia (MM) 2024
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2025
International Joint Conference on Neural Networks (IJCNN) 2025

Teaching

Teaching Assistant / Tutor at CityUHK (2021~2025): CS1102, CS5187, CS4186, CS2313

Bolin Chen (陈柏林)