|
Wei GAO (高伟)
Associate Professor (with Tenure)
Ph.D. Supervisor, IEEE Senior Member Associate Editor of IEEE TIP/TCSVT/TMM PI of Multimedia Computing and AI Lab (MMCAL) School of Electronic and Computer Engineering, Peking University 北京大学信息工程学院（深圳） |
   |
  
|
[Biography] [Research] [Team] [Publications] [Patents] [ReferenceMaterials] [Teaching] [Awards] [Activities] [OpenSourceProjects] [Gallery] [Visitors]
Recent News
- 目前课题组还有2026年9月入学考研硕士生名额2个，欢迎联系申请加入课题组！
- 课题组常年招聘博士后，招收学术型博士生、硕士生，招收若干本科生科研实习生！
- We have opening positions for Postdoc Fellows at Peking University！
- We are looking for self-motivated Ph.D. and M.Phil. Students at Peking University！
- 2026/07 -- One paper was accepted to IEEE TIP!
- 2026/07 -- Five papers were accepted to ACM MM 2026!
- 2026/05 -- Our paper titled "DiffPCGC: Efficient Point Cloud Geometry Compression via Diffusion Models" received the 2026 IEEE CASS Multimedia Systems and Applications Technical Committee (MSA-TC) Best Paper Award!
- 2026/04 -- One paper was accepted to IEEE TCSVT!
- 2026/03 -- One paper was accepted to IEEE TIP!
- 2026/03 -- One paper was accepted to IEEE TIM!
- 2026/03 -- One paper was accepted to IEEE TBC!
- 2026/02 -- I was invited to serve as Area Chair for ACM MM 2026!
- 2026/02 -- One paper was accepted to CVPR 2026!
- 2026/02 -- One paper was accepted to ICRA 2026!
- 2026/01 -- Two papers were accepted to ICLR 2026!
- 2026/01 -- I was invited to serve as Senior Program Committee (SPC) Member for IJCAI-ECAI 2026!
- 2026/01 -- One paper was accepted to IEEE TIP!
More in 2025 and Before
- 2025/12 -- One paper was accepted to IEEE TBC!
- 2025/12 -- I was a recipient of IEEE Visual Signal Processing and Communications (VSPC) Rising Star (Honorable Mention Award) for Contributions in 3D Visual Data Coding!
- 2025/12 -- I was appointed as Associate Editor for IEEE Transactions on Image Processing (IEEE TIP)!
- 2025/11 -- One paper was accepted to AAAI 2026!
- 2025/10 -- I was appointed as Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)!
- 2025/10 -- I was appointed as Associate Editor for IEEE Transactions on Multimedia (IEEE TMM)!
- 2025/09 -- I was selected to 2025 Stanford University “The World’s Top 2% Scientists” List!
- 2025/08 -- One paper was accepted to ACM MobiCom 2025!
- 2025/07 -- One paper was accepted to IEEE TPAMI! This paper provides a comprehensive survey for the research of deep learning-based point cloud compression.
- 2025/07 -- Four papers were accepted to ACM MM 2025!
- 2025/07 -- I was Elected as a Member of IEEE Multimedia Systems and Applications Technical Committee (IEEE MSA-TC)!
- 2025/06 -- Three papers were accepted to ICCV 2025!
- 2025/06 -- One paper was accepted to IEEE TIP!
- 2025/06 -- We received the 2025 Springer Nature - China New Development Awards!
- 2025/05 -- I was appointed as Associate Editor for ACM Transactions on Multimedia Computing, Communications, and Applications (ACM TOMM)!
- 2025/04 -- One paper was accepted to IJCAI 2025!
- 2025/04 -- One paper was accepted to IEEE TETCI!
- 2025/04 -- My course “3D Vision & Computational Photography” was admitted to Peking University Graduate Course Construction Funding Project!
- 2025/04 -- I was invited to serve as Area Chair for NeurIPS 2025!
- 2025/03 -- I was invited to serve as Area Chair for ACM MM 2025!
- 2025/02 -- We are organizing the International Workshop on Application-driven Point Cloud Processing and 3D Vision (APP3DV) (Webpage) at ACM MM 2025. Submission deadline: 11 July, 2025. Welcome to submit papers!
- 2025/02 -- I will be the Tutorial Speaker for the Tutorial on AI-based Multimedia Data Compression: Perception Utility Optimization and Standardization (AIMDC) at ACM MM 2025!
- 2024/12 -- Four papers were accepted to AAAI 2025!
- 2024/11 -- One paper was accepted to IEEE TBC!
- 2024/11 -- As the first recipient, we won the Second Prize of the Natural Science Award of the China Society of Image and Graphics in 2024 (Theories and Methods for Multimodal Visual Perception with Restricted Environments, Ranked 1)!
- 2024/11 -- One paper was accepted to IEEE TIP!
- 2024/11 -- One paper was accepted to IEEE JBHI!
- 2024/10 -- One paper was accepted to IEEE TIM!
- 2024/10 -- One paper was accepted to IEEE TNNLS!
- 2024/09 -- Two papers were accepted to NeurIPS 2024!
- 2024/07 -- Seven papers were accepted to ACM MM 2024!
- 2024/07 -- I will be the Tutorial Speaker for the Tutorial on Point Cloud Compression, Enhancement and Applications: From 3D Perception to Large Models (3DPC-APC) at ACM MM 2024!
- 2024/07 -- One paper was accepted to ECCV 2024!
- 2024/06 -- One paper was accepted to IEEE TGRS!
- 2024/05 -- One paper was accepted to IEEE TCSVT!
- 2024/04 -- One paper was accepted to IEEE TCSVT!
- 2024/04 -- Our team was the third-place winner of the Competition for NTIRE 2024 Quality Assessment for AI-Generated Content - Track 2 Video! (Webpage)!
- 2024/04 -- As the Co-lead Guest Editor, we are releasing the Call-for-papers for Special Issue on Deep Learning-Based Data Compression in APSIPA Transactions on Signal and Information Processing (APSIPA SIP)! (Webpage)!
- 2024/03 -- We won the AVS Industrial Technology Innovation Team Award (For Contributions to Point Cloud Compression Standard) in 2023!
- 2024/03 -- Our Paper titled "Research Progress in 3D Point Cloud Compression Technologies and Standards" was published in Communications of China Society of Image and Graphics (Webpage)!
- 2024/02 -- I was appointed as Associate Editor for APSIPA Transactions on Signal and Information Processing (APSIPA SIP)!
- 2024/01 -- One paper was accepted to IEEE TCSVT!
- 2024/01 -- I will be the Tutorial Speaker for the Tutorial on Neural Network Design and Optimization for 3D Point Cloud Computing (NNPC) at IEEE IJCNN 2024!
- 2024/01 -- I will be the Tutorial Speaker for the Tutorial on Point Cloud Coding, Enhancement and Analysis: Towards Perception and Reliability (PCEA) at IEEE ICIP 2024!
- 2024/01 -- One paper was accepted to IEEE TITS!
- 2023/12 -- Three papers were accepted to AAAI 2024!
- 2023/11 -- One paper was accepted to IJCV!
- 2023/11 -- One paper was accepted to IEEE TIP!
- 2023/09 -- We participated in the drafting of China's AI series white paper on deep learning (Webpage)!
- 2023/09 -- One paper was accepted to IEEE TGRS!
- 2023/09 -- One paper was accepted to IEEE TIM!
- 2023/08 -- One paper was accepted to IEEE TIP!
- 2023/07 -- Five papers were accepted to ACM MM 2023!
- 2022/07 -- One paper was recognized as Popular Documents (the 50 most frequently accessed documents - July 2022) in IEEE TPAMI!
- 2023/07 -- One paper was accepted to ICCV 2023!
- 2023/05 -- I was Elevated to the grade of CSIG Senior Member!
- 2023/05 -- One paper was accepted to IEEE TCSVT!
- 2023/04 -- One paper was accepted to IEEE TNNLS!
- 2023/04 -- One paper was accepted to IEEE MultiMedia!
- 2023/02 -- One paper was accepted to CVPR 2023!
- 2023/01 -- I was Elected as a Member of IEEE Visual Signal Processing and Communications Technical Committee (IEEE VSPC-TC)!
- 2023/01 -- We are organizing the International Workshop on Perception-inspired Communication and Processing for Immersive and Interactive Multimedia (PCPI2M) (Webpage) at IEEE ICME 2023. Submission deadline: March 23, 2023. Welcome to submit papers!
- 2023/01 -- Two papers were accepted to IEEE TCSVT!
- 2022/12 -- I will be the Tutorial Speaker for the Tutorial on 3D Point Cloud Compression and Processing for Multi-dimensional Applied Perception (PCP-MAP) at IEEE ICME 2023!
- 2022/12 -- One paper was accepted to IEEE TPAMI!
- 2022/12 -- Two papers received the Shenzhen Excellent Research Paper Award in Science and Technology!
- 2022/10 -- One paper was accepted to IEEE TGRS!
- 2022/09 -- The general project “Key Technologies of Visual Perception Based 3D Point Cloud Coding” (PI) was funded by NSFC!
- 2022/08 -- We received the 2022 CCF Excellent Open Source Graphic Software Nomination Award!
- 2022/07 -- One paper was accepted to ECCV 2022!
- 2022/06 -- Three papers were accepted to ACM MM 2022!
- 2022/06 -- One paper was accepted to IEEE TCSVT!
- 2022/06 -- One paper was accepted to IEEE TNNLS!
- 2022/05 -- One paper was recognized as Popular Documents (the 50 most frequently accessed documents - April 2022) in IEEE TCSVT!
- 2022/05 -- We are organizing the Special Session on 3D Point Cloud Acquisition, Processing and Communication (3DPC-APC) at IEEE VCIP 2022 (Webpage). Submission deadline: June 5, 2022. Welcome to submit papers!
- 2022/04 -- One paper was accepted to IEEE TCSVT!
- 2022/04 -- I was Elevated to the grade of CCF Senior Member!
- 2022/04 -- We are organizing the International Workshop on Advances in Point Cloud Compression, Processing and Analysis (APCCPA) at ACM MM 2022 (Webpage). Submission deadline: July 4, 2022. Welcome to submit papers!
- 2022/03 -- One paper was accepted to IEEE TMM!
- 2022/03 -- One paper was accepted to CVPR 2022!
- 2022/02 -- I was Elevated to the grade of IEEE Senior Member!
- 2022/02 -- One paper was accepted to IEEE TII!
- 2022/01 -- I was appointed as Associate Editor for Signal Processing (Elsevier SIGPRO)!
- 2022/01 -- I was Elected as the Member of Image, Video, and Multimedia Technical Committee, Asia-Pacific Signal and Information Processing Association (APSIPA IVM-TC)!
Biography
-
Wei Gao is currently a Tenured Associate Professor/Ph.D. Supervisor/PI at the School of Electronic and Computer Engineering, Peking University, China. He is now leading the Multimedia Computing and AI Lab (MMCAL). His research interests include Multimedia Computing and Artificial Intelligence, especially 3D Visual Intelligence, Multimodal Intelligence, and Applications (Immersive Media, Autonomous Driving/Robotics). He is a Senior Member of IEEE.
Research: He has published over 200 research papers in international journals (IEEE TPAMI/TIP/TCSVT/TMM/TNNLS/TGRS and IJCV, etc.) and international conferences (CVPR/ICCV/ECCV/ACM MM/AAAI/NeurIPS/ICLR, etc.). He authored four books published by Springer Nature, including “AI-based 3D Point Cloud Coding”, “AI-based Image and Video Coding”, “Deep Learning for 3D Point Clouds”, and “Point Cloud Compression”, and received the 2025 Springer Nature - China New Development Awards. He participated in the drafting of China's AI series white paper on deep learning in 2023. He has applied over 80 US/China patents (40+ Granted), and submitted over 80 MPEG/AVS standard proposals (30+ Adopted). He is actively participating in the development of multimedia and artificial intelligence standards. He participated in the establishment of group standards for “Information Technology - High Efficiency Graphics Data Coding, Part 2: Point Clouds” and “Information Technology - High Efficiency Graphics Data Coding, Part 3: Subjective Quality Assessment Methods for Point Clouds”. He is one of the key contributors to the first and second generation China point cloud compression standards. He received the 2023 AVS Industrial Technology Innovation Team Award (For Contributions to Point Cloud Compression Standard). He established several open source projects, including OpenPointCloud (Point Cloud Coding and Processing), OpenAICoding (Deep Learning-based Image/Video Coding), OpenAIDriving (AI-based Autonomous Driving), OpenDatasets (Datasets for Multimedia Computing and AI). He received the China Computer Federation Excellent Open Source Graphics Software Award in 2022. He was selected to Stanford University “The World’s Top 2% Scientists” List. He received the Second Prize of the Natural Science Award of the China Society of Image and Graphics in 2024 (Theories and Methods for Multimodal Visual Perception with Restricted Environments, as the First Recipient). He was a recipient of IEEE Visual Signal Processing and Communications (VSPC) Rising Star (Honorable Mention Award) in 2025. He was a recipient of the IEEE Multimedia Rising Star (Runner Up Award) for Outstanding Early-stage Career Achievements in the Area of 3D Immersive Media Research in 2021. He received the China Computer Federation Tencent Rhino Bird Excellent Patent Award in 2021. He was a recipient of the IEEE CASS Multimedia Systems and Applications Technical Committee (MSA-TC) Best Paper Award in 2026 (As the Corresponding Author). He has undertaken more than 20 government-funded and industry-funded research projects, including National Key R&D Program, National Natural Science Foundation, Guangdong Provincial Natural Science Foundation, Shenzhen City Natural Science Foundation.
Teaching: He has been teaching two courses to Ph.D. and M.Phil. students at Peking University since 2019, including “3D Vision & Computational Photography” and “Selected Topics in Advanced Video Processing”. His course “3D Vision & Computational Photography” was admitted to Peking University Graduate Course Construction Funding Project in 2024, and was admitted to the Shared Course Program of the University Town of Shenzhen. He has supervised or is supervising more than 50 Ph.D. and M.Phil. graduate students, and they have received many distinguished awards and honors, including the National Scholarship, Excellent Graduate of Beijing City, Excellent Graduate of Peking University, Merit Student Elite of Peking University, and 2024 Shenzhen Outstanding Doctoral Dissertation Award for Artificial Intelligence, 2026 IEEE CASS Multimedia Systems and Applications Technical Committee (MSA-TC) Best Paper Award.
Service: He is an Elected Member of IEEE Multimedia Systems and Applications Technical Committee (IEEE MSA-TC), an Elected Member of IEEE Visual Signal Processing and Communications Technical Committee (IEEE VSPC-TC), and an Elected Member of APSIPA Image Video and Multimedia Technical Committee (APSIPA IVM-TC). He is an Elected Member of China Computer Federation Technical Committee on Multimedia Technology (CCF TCMM), and an Elected Member of China Society of Image and Graphics Technical Committee on Multimedia (CSIG TCMM), CSIG Technical Committee on 3D Vision (CSIG TC3DV), CSIG Technical Committee on Image and Video Communications (CSIG TCIVC). He is currently Associate Editor for IEEE Transactions on Image Processing (IEEE TIP), IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), IEEE Transactions on Multimedia (IEEE TMM). He was the Guest Editor for Special Issue on Deep Learning-Based Data Compression in APSIPA Transactions on Signal and Information Processing in 2024, and Special Issue on 3D Point Cloud Processing and Applications in ZTE Communications in 2023. He organized workshops and special sessions at ACM MM 2025, IEEE ICME 2023, ACM MM 2022, IEEE VCIP 2022, and IEEE ICME 2021. He was the tutorial speaker at ACM MM 2025, ACM MM 2024, IEEE ICIP 2024, IEEE IJCNN 2024, and IEEE ICME 2023. He has served as the reviewer for international top journals including IEEE TPAMI, TIP, TVCG, TCSVT, TMM, TNNLS, as well as international top conferences including NeurIPS, CVPR, ECCV, AAAI, ACM MM, IJCAI, ICLR. He has served as Area Chair for international top conferences. He has served as the reviewer of NSFC funds and other project funds.
Lab Goal: He founded MMCAL in 2019, and is now leading the research team to work on the advanced technologies of immersive media and 3D vision. The research team aims to promote the developments of emerging 3D visual intelligence technologies for the benefits of both human and machine perception. The key application fields include immersive interactive media communication (VR/AR/MR) and autonomous intelligent unmanned systems (autonomous driving/robotics). The research team has extensive research collaborations with the industry to promote the applications of related technologies in the field of intelligent 3D visual data processing.
- 高伟，北京大学长聘副教授/研究员/博士生导师/PI。北京大学多媒体计算与智能实验室（MMCAL）负责人，北京大学视频与视觉技术国家工程研究中心（深圳）成员、广东省超高清沉浸媒体技术重点实验室成员。广东省高层次人才、深圳市孔雀计划人才。曾在香港城市大学、新加坡南洋理工大学和美国UCLA学习和工作，曾在工业界从事研发工作。长期从事多媒体计算与人工智能领域研究，特别是3D视觉智能、多模态智能及应用（沉浸媒体、自动驾驶/机器人）。研究方向主要包括：（1）3D视觉数据智能编码与处理：3D视觉数据编码（3D点云编码、3D Gaussian Splatting压缩/渲染、2D/3D图像视频编码、深度学习智能编码、人机感知共友好编码）、3D视觉数据质量评价与增强、智能编码标准与传输系统；（2）空间智能与具身智能：面向3D重建生成的生成式人工智能/世界模型、面向3D感知理解的视觉-语言-动作多模态大模型、空间智能与具身智能的3D视觉与多模态学习。
深入开展3D视觉智能与多模态智能理论与方法研究，推动相关技术在沉浸交互媒体通信（VR/AR/MR）、自主智能无人系统（自动驾驶/机器人）领域的应用。
IEEE/CCF/CSIG Senior Member。
科研方面：在国际权威期刊（如IEEE TPAMI、TIP、TCSVT、TMM、TNNLS、TGRS和IJCV等）和国际重要会议（如CVPR、ICCV、ECCV、ACM MM、AAAI、NeurIPS、ICLR等）上发表论文200余篇，多篇论文入选ESI高被引论文和优秀论文奖。编写英文学术专著4部，包括《AI-based 3D Point Cloud Coding》、《AI-based Image and Video Coding》、《Deep Learning for 3D Point Clouds》、《Point Cloud Compression》，并荣获2025年施普林格·自然“中国新发展奖”。参与2023年中国人工智能系列白皮书《深度学习》编写工作。申请美国/中国专利80余项（已授权40余项），提交国际MPEG和国内AVS标准技术提案80余项（被采纳30余项）。积极参与多媒体与人工智能技术标准制定工作，参与《信息技术 高效图形数据编码 第2部分：点云》、《信息技术 高效图形数据编码 第3部分：点云主观质量评价方法》团体标准立项，作为核心成员积极参与推动第一代和第二代中国自主点云编码标准，并荣获2023年AVS产业技术创新奖团队奖（点云压缩标准贡献）。搭建多个重要开源项目，包括OpenPointCloud（点云编码与处理开源库）、OpenAICoding（深度学习图像视频编码开源库）、OpenAIDriving（基于人工智能的自动驾驶开源库）、OpenDatasets（多媒体计算与人工智能数据集开源库）等，并荣获2022年中国计算机学会优秀图形开源软件奖项。入选斯坦福大学“全球前2%顶尖科学家”榜单。荣获2024年度中国图象图形学学会自然科学奖二等奖（受限环境下多模态视觉感知理论与方法，第1完成人）。由于3D视觉数据编码方面的研究工作荣获2025年国际IEEE视觉信号处理与通信学术新星奖项。由于3D沉浸式媒体方面的研究工作荣获2021年国际IEEE多媒体学术新星奖项。荣获2021年中国计算机学会腾讯犀牛鸟优秀专利奖。荣获2026年国际IEEE多媒体系统与应用技术委员会最佳论文奖（通信作者）。作为负责人承担20余项国家级、省市级和企业合作重要科研项目，包括科技部国家重点研发计划项目（课题3项）、国家自然科学基金项目（重点项目课题1项，面上项目1项，青年项目1项）、广东省自然科学基金项目（面上项目2项）、深圳市基础研究项目（重点项目1项，面上项目3项）等。
教学方面：自2019年起为北京大学硕博研究生讲授两门课程，包括《三维视觉与计算摄像学》、《现代视频处理专题》。所开设的课程《三维视觉与计算摄像学》获得2024年北京大学研究生课程建设资助立项并入选深圳大学城公开课共享课程。指导博士后/博士生/硕士生累计50余人，所指导的博士/硕士研究生多人次获得国家奖学金、北京市优秀毕业生、北京大学优秀毕业生、北京大学三好学生标兵，以及2024年深圳人工智能优秀博士学位论文奖、2026年国际IEEE多媒体系统与应用技术委员会最佳论文奖等荣誉。
服务方面：担任国际IEEE多媒体系统与应用技术委员会委员（IEEE MSA-TC）、国际IEEE视觉信号处理和通信技术委员会委员（IEEE VSPC-TC）、亚太信号与信息处理协会图像视频与多媒体技术委员会委员（APSIPA IVM-TC）。担任中国计算机学会多媒体技术专委会执行委员、中国图象图形学学会多媒体专业委员会委员/三维视觉专业委员会委员/图像视频通信专业委员会委员。担任多媒体计算与人工智能领域多个国际顶级期刊副编辑，包括IEEE Transactions on Image Processing (IEEE TIP)、IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)、IEEE Transactions on Multimedia (IEEE TMM)等。担任APSIPA Transactions on Signal and Information Processing、ZTE Communications期刊上深度学习数据压缩、点云处理与应用专刊的客座编委。在ACM MM 2025、IEEE ICME 2023、ACM MM 2022、IEEE VCIP 2022、IEEE ICME 2021会议上组织过点云编码与处理、3D视觉计算与应用、交互式媒体质量评价等领域的研讨会和专题会议。担任ACM MM 2025、ACM MM 2024、IEEE ICIP 2024、IEEE IJCNN 2024、IEEE ICME 2023讲习班讲者。担任国际顶级期刊IEEE TPAMI、TIP、TVCG、TCSVT、TMM、TNNLS，以及国际顶级会议NeurIPS、CVPR、ECCV、AAAI、ACM MM、IJCAI、ICLR等审稿人，多次担任国际顶级会议领域主席等。国家自然科学基金和省市级项目评审专家。
实验室使命：2019年创立了北京大学多媒体计算与智能实验室（MMCAL），正在带领课题组积极从事沉浸媒体与3D视觉技术研究。课题组致力于促进新兴3D视觉智能与多模态智能技术发展，以更好地服务于人类与机器感知。重要应用领域包括沉浸交互媒体通信（VR/AR/MR）、自主智能无人系统（自动驾驶/机器人）等。课题组与工业界有广泛的研发合作，推动相关技术应用落地。
欢迎优秀的本科生和硕士生保送和报考北京大学信息工程学院的博士和硕士研究生（招生要求：自我驱动，主动性强，有清晰的工作目标；热爱从事科研工作或有强烈创业想法；工程能力强，能独立完成创新工作；有团队意识，注重参与集体协作任务；有以第一作者身份发表IEEE Transactions和CCF A类论文或获得高水平编程竞赛奖励等经验者优先），同时欢迎申请课题组的博士后和访问职位（近年来课题组已经招收多名优秀博士后开展高水平研究工作，均来自于中山大学、北京理工大学、四川大学、英国谢菲尔德大学等国内外知名高校），共同从事多媒体计算与人工智能相关热门与前沿课题的研究探索。
Research
- We are focusing on Multimedia Computing and Artificial Intelligence, especially 3D Visual Intelligence, Multimodal Intelligence, and Applications.
- Intelligent 3D Visual Data Coding and Processing:
3D Visual Data Coding (3D Point Cloud Coding, 3D Gaussian Splatting Compression/Rendering, 2D/3D Image/Video Coding, Deep Learning-Based Coding, Human and Machine Perception-Driven Coding)
3D Visual Data Quality Assessment and Enhancement
AI-based Coding Standards and Transmission Systems
- Spatial Intelligence and Embodied Intelligence:
Generative AI/World Models for 3D Reconstruction/Generation
Vision-Language-Action (VLA) Models for 3D Perception/Understanding
3D Vision and Multimodal Learning for Spatial Intelligence and Embodied Intelligence
- We aim to conduct in-depth research on the theories and methods of 3D visual intelligence and multimodal intelligence, and promote the application of related technologies in immersive interactive media communication (VR/AR/MR) and autonomous intelligent unmanned systems (autonomous driving/robotics).
Other Research Topics
- Saliency Segmentation for RGB-D/RGB-T/Light Field/Point Cloud (See TPAMI 2023: A Thorough Benchmark and A New Model for Light Field Saliency Detection)
- Model Compression and Acceleration (See IJCV 2024: Interpretable Task-inspired Adaptive Filter Pruning for Neural Networks Under Multiple Constraints)
- FPGA/ASIC and Embedded Systems (See ACM MM 2023: OpenHardwareVC: An Open Source Library for 8K UHD Video Coding Hardware Implementation)
- Open Source Projects (See ACM MM 2022: OpenPointCloud: An Open-Source Algorithm Library of Deep Learning Based Point Cloud Compression)
Team
-
Postdoctoral Fellow positions are opening at Peking University.
Ph.D. and M.Phil. positions are opening at Peking University (including the Joint Ph.D. Program with Peng Cheng Laboratory).
Please feel free to send your CV and the supporting documents (certificates and transcripts, publications, research proposal, etc.) via Email.
Publications |
|
|
Patents & Standardizations
Reference Materials
- We have edited four reference books:
- AI-based 3D Point Cloud Coding: Methods, Standards, and Applications, Springer Nature, April 2026. (Webpage)
- AI-based Image and Video Coding: Methods, Standards, and Applications, Springer Nature, August 2025. (Webpage)
- Deep Learning for 3D Point Clouds, Springer Nature, December 2024. (Webpage)
- Point Cloud Compression: Technologies and Standardization, Springer Nature, May 2024. (Webpage)
Teaching
- I am teaching the following courses for postgraduate students (Ph.D. and M.Phil.) at Peking University:
- 3D Vision & Computational Photography (Fall Semester)
- Selected Topics in Advanced Video Processing (Spring Semester)
Awards
- 2026 IEEE CASS Multimedia Systems and Applications Technical Committee Best Paper Award (DiffPCGC: Efficient Point Cloud Geometry Compression via Diffusion Models, As the Corresponding Author)
- 2025 IEEE Visual Signal Processing and Communications (VSPC) Rising Star (Honorable Mention Award)
- 2025 Stanford University “The World’s Top 2% Scientists” List
- 2025 Springer Nature - China New Development Awards
- 2024 CSIG Natural Science Award - Second Prize (Theories and Methods for Multimodal Vision Perception with Restricted Environments, As the First Recipient)
- 2023 AVS Industrial Technology Innovation Team Award (For Contributions to Point Cloud Compression Standard)
- 2022 CCF Excellent Open Source Graphics Software Nomination Award (As the First Recipient)
- 2021 CCF-Tencent Rhino-Bird Excellent Patent Award (As the First Recipient)
- 2021 IEEE Multimedia Rising Star (Runner Up Award) for Outstanding Early-stage Career Achievements in the Area of 3D Immersive Media Research
Professional Activities
Membership:- Senior Member of IEEE
- Senior Member of China CCF/CSIG
- Elected Member, IEEE Multimedia Systems and Applications Technical Committee (IEEE MSA-TC, 2025.9-2029.8)
- Elected Member, IEEE Visual Signal Processing and Communications Technical Committee (IEEE VSPC-TC, 2023.1-2026.12)
- Elected Member, APSIPA Image Video and Multimedia Technical Committee (APSIPA IVM-TC, 2022.1-2024.12)
- Elected Member, CCF Technical Committee on Multimedia Technology (CCF TCMM, 2022.7-)
- Elected Member, CSIG Technical Committee on Multimedia (CSIG TCMM, 2022.7-)
- Elected Member, CSIG Technical Committee on 3D Vision (CSIG TC3DV, 2022.12-)
- Elected Member, CSIG Technical Committee on Image and Video Communications (CSIG TCIVC, 2024.7-)
- Associate Editor, IEEE Transactions on Image Processing (IEEE TIP, 2025.12-)
- Associate Editor, IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT, 2025.11-)
- Associate Editor, IEEE Transactions on Multimedia (IEEE TMM, 2025.10-)
- Associate Editor, ACM Transactions on Multimedia Computing, Communications, and Applications (ACM TOMM, 2025.5-)
- Associate Editor, Signal Processing (Elsevier SIGPRO, 2022.1-)
- Guest Editor of Special Issue, Deep Learning-Based Data Compression at APSIPA Transactions on Signal and Information Processing, 2024
- Guest Editor of Special Issue, 3D Point Cloud Processing and Applications at ZTE Communications, 2023
- Tutorial Speaker, AI-based Multimedia Data Compression: Perception Utility Optimization and Standardization (AIMDC) at ACM MM 2025
- Tutorial Speaker, Point Cloud Compression, Enhancement and Applications: From 3D Perception to Large Models (PC3DPLM) at ACM MM 2024
- Tutorial Speaker, Neural Network Design and Optimization for 3D Point Cloud Computing (NNPC) at IEEE IJCNN 2024
- Tutorial Speaker, Point Cloud Coding, Enhancement and Analysis: Towards Perception and Reliability (PCEA) at IEEE ICIP 2024
- Tutorial Speaker, 3D Point Cloud Compression and Processing for Multi-dimensional Applied Perception (PCP-MAP) at IEEE ICME 2023
- Lead Workshop Organizer, Application-driven Point Cloud Processing and 3D Vision (APP3DV) at ACM MM 2025 (Webpage)
- Lead Workshop Organizer, Perception-inspired Communication and Processing for Immersive and Interactive Multimedia (PCPI2M) at IEEE ICME 2023 (Webpage)
- Lead Workshop Organizer, Advances in Point Cloud Compression, Processing and Analysis (APCCPA) at ACM MM 2022 (Webpage)
- Workshop Organizer, Quality of Experience in Interactive Multimedia (QoEIM) at IEEE ICME 2021 (Webpage)
- Lead Special Session Organizer, 3D Point Cloud Acquisition, Processing and Communication (3DPC-APC) at IEEE VCIP 2022 (Webpage)
- Competition Chair of Local Arrangement Committee, International Joint Conferences on Artificial Intelligence (IJCAI) 2023
- Area Chair (AC) for ACM MM 2026
- Senior Program Committee (SPC) Member for IJCAI-ECAI 2026
- Area Chair (AC) for NeurIPS 2025, ACM MM 2025
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Image Processing (TIP)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- IEEE Transactions on Multimedia (TMM)
- IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
- IEEE Transactions on Mobile Computing (TMC)
- IEEE Transactions on Geoscience and Remote Sensing (TGRS)
- IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS)
- IEEE Transactions on Cybernetics (TCYB)
- IEEE Transactions on Broadcasting (TBC)
- IEEE Transactions on Visualization and Computer Graphics (TVCG)
- IEEE Transactions on Industrial Electronics (TIE)
- IEEE Transactions on Industrial Informatics (TII)
- IEEE Transactions on Circuits and Systems I: Regular Papers (TCAS-I)
- IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS-II)
- IEEE Signal Processing Letters (SPL)
- International Journal of Computer Vision (IJCV)
- Signal Processing (SIGPRO)
- Neurocomputing (NEUCOM)
- Information Sciences (INS)
- Signal Processing: Image Communication (SPIC)
- APSIPA Transactions on Signal and Information Processing (APSIPA SIP)
- International Journal of Applied Earth Observation and Geoinformation (JAG)
- IET Image Processing (IET IPR)
- International Conference on Machine Learning (ICML)
- International Conference on Learning Representations (ICLR)
- Neural Information Processing Systems (NeurIPS)
- IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR)
- European Conference on Computer Vision (ECCV)
- AAAI Conference on Artificial Intelligence (AAAI)
- International Joint Conferences on Artificial Intelligence (IJCAI)
- ACM International Conference on Multimedia (ACM MM)
- IEEE International Conference on Multimedia and Expo (ICME)
- IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
- IEEE International Conference on Visual Communication and Image Processing (VCIP)
- International Conference on Pattern Recognition (ICPR)
- Picture Coding Symposium (PCS)
Open Source Projects
- OpenPointCloud (Open Source Project for Point Cloud Coding and Processing)
- OpenAICoding (Open Source Project for Deep Learning-based Image/Video Coding)
- OpenAIDriving (Open Source Project for AI-based Autonomous Driving)
- OpenAIRobotics (Open Source Project for AI-based Robotics) (Under Construction)
- OpenDatasets (Open Datasets for Multimedia Computing and AI)
Gallery
