丁丹丹
一、导师基本情况
姓名：丁丹丹 教授
邮箱：DandanDing@hznu.edu.cn, 187113186 (QQ)
指导专业：计算机科学与技术，软件工程（电子信息硕士），网络空间安全等
课题组网站：https://github.com/3dpcc、https://dandanding.com/
二、研究领域
1. 智能多媒体通信：智能视频编码、三维点云压缩与传输
2. 多模态视觉计算：跨模态表征学习、生成式建模、3D重建与理解
3. 视频生成大模型：高效推理机制、生成质量评价与优化
4. AI芯片协同设计：基于NPU/SoC的端到端压缩、传输与端侧部署
三、主讲课程
《操作系统》《计算机网络》等
四、教育和工作经历
2006年于浙江大学通信工程专业毕业，2007至2008年于瑞士EPFL交流学习，2011年获浙江大学通信与信息系统博士学位，2011至2015年于浙江大学工作，2016至今于杭州师范大学工作。
五、学术简介
IEEE高级会员，中国人工智能学会元宇宙技术专委会委员、中国指挥与控制学会富媒体指挥专业委员会委员，IEEE视觉信号处理与通信（VSPC）技术委员会成员。主要研究领域为全息多媒体通信、智能视觉数据编码、AI芯片设计等。
发表国内外高水平论文90余篇，包括Proceedings of the IEEE, TPAMI, TIP, TVCG, TCSVT, TMM等多媒体与计算机视觉领域的TOP期刊，以及CVPR, ICML, AAAI, IJCAI, ACMMM等CCF推荐A类会议。申请发明专利30余项，向国内外标准组织提交提案40项。承担国家自然科学基金面上项目2项，省自然科学基金项目2项，企业合作项目10余项。与行业领先企业（例如Google公司、阿里巴巴等）、国外高校，以及国内多所985高校有持续、紧密合作。参与多项国际/国家标准制定，曾担任ISO/IEC标准23001-1与23001-2的Project Leader，获得ISO/IEC标准制定嘉奖，担任中国音视频编码标准AVS-13联合组长，目前担任面向机器视觉编码工作组点云组联合主席。
担任IEEE Signal Processing Letters期刊Associate Editor，担任多个知名国际会议（如ICASSP、ICME、MMSP等）Area Chair与论坛主席。
实验室简介：智能视频编码实验室已培养毕业研究生近20名，就业率达100%。毕业生就职于视频编码、图像处理、芯片设计等领域的知名企事业单位。其中，4名硕士研究生升学至南京大学、南京航空航天大学攻读博士学位。累计指导本科生20余名，分别赴中国科学院大学、中国科学技术大学、北京航空航天大学，以及美国普渡大学、澳大利亚新南威尔士大学等国内外一流高校继续深造。实验室荣获学院及学校“十佳研究生优良作风团队”荣誉称号。
欢迎热爱技术、乐于探索的同学加入实验室，一起把想法玩出新高度。
六、主持教学科研项目
1. 国家自然科学基金面上项目：面向高动态复杂场景的多模态视觉数据紧致编码与压缩域推理，2026.1-2029.12.
2. 国家自然科学基金面上项目：面向边缘智能的原始成像数据理解与编码，2022.1-2025.12.
3. 浙江省自然科学基金项目：基于深度神经网络的视频编码关键算法研究及全局优化，2020.1-2022.12.
4. ******：AI+视频编码芯片设计与部署，2026.4-2027.10
5. Google公司合作项目：下一代AV2高效视频编码方法研究，2018.9-2026.10
6. 阿里巴巴公司合作项目：视频编码、大模型优化等，2024.3-2027.3
七、代表性论著（#共同作者，*通信作者）
近期发表期刊论文：
[1] J. Zhang, T. Chen, D. Ding*, and Z. Ma*, "Neural compression system for point cloud video streaming," IEEE TIP, vol. 34, pp. 8032-8045, 2025.
[2] Z. Li, J. Zhu, D. Ding*, and Z. Ma, "Improving occupancy prediction for multiscale point cloud geometry compression," IEEE TCSVT, vol. 35, no. 7, pp. 7200-7210, 2025.
[3] J. Zhang, T. Chen, D. Ding*, and Z. Ma, "Revisit point cloud quality assessment: Current advances and a multiscale-inspired approach," IEEE TVCG, vol. 31, no. 10, pp. 8886-8899, 2025.
[4] W. Wang, J. Yao, G. Yu, X. Bian, and D. Ding*, "Edge detection-driven LightGBM for fast intra partition of H.266/VVC," JVCI, vol. 98, p. 104606, 2025.
[5] J. Zhang, J. Zhang, D. Ding*, and Z. Ma, "ARNet: Attribute artifacts reduction for G-PCC compressed point clouds," Comput. Visual Media, vol. 11, no. 2, pp. 327-342, Apr. 2025.
[6] J. Zhang, T. Chen, K. You, D. Ding*, and Z. Ma, "ConPCAC: Conditional lossless point cloud attribute compression via spatial decomposition," IEEE TCSVT, vol. 35, no. 7, pp. 7210-7221, 2025.
[7] J. Zhang, G. Liu, J. Zhang, D. Ding*, and Z. Ma, "DeepPCC: Learned lossy point cloud compression," IEEE TETCI, vol. 9, no. 2, pp. 1897-1909, Apr. 2025.
[8] J. Zhang, J. Zhang, D. Ding*, and Z. Ma, "Learning to restore compressed point cloud attribute: A fully data-driven approach and a rules-unrolling-based optimization," IEEE TVCG, vol. 31, no. 4, pp. 1985-1998, Apr. 2025.
[9] J. Wang, R. Xue, J. Li, D. Ding, Y. Lin, and Z. Ma, "A versatile point cloud compressor using universal multiscale conditional coding - Part I: Geometry," IEEE TPAMI, vol. 47, no. 1, pp. 269-287, Jan. 2025.
[10] J. Wang, R. Xue, J. Li, D. Ding, Y. Lin, and Z. Ma, "A versatile point cloud compressor using universal multiscale conditional coding - Part II: Attribute," IEEE TPAMI, vol. 47, no. 1, pp. 252-268, Jan. 2025.
[11] J. Zhang, J. Wang, D. Ding*, and Z. Ma, "Scalable point cloud attribute compression," IEEE TMM, vol. 27, pp. 889-899, 2025. [高被引论文]
[12] J. Zhang, J. Zhang, W. Ma, D. Ding*, and Z. Ma, "Content-aware rate control for geometry-based point cloud compression," IEEE TCSVT, vol. 34, no. 10, pp. 9550-9561, Oct. 2024.
[13] Y. Zhang, D. Ding*, Z. Ma, and Z. Li, "A reconfigurable framework for neural network-based video in-loop filtering," ACM TOMM, vol. 20, no. 4, pp. 1-22, 2024.
[14] G. Liu, R. Xue, J. Li, D. Ding*, and Z. Ma, "GRNet: Geometry restoration for G-PCC compressed point clouds using auxiliary density signaling," IEEE TVCG, vol. 30, no. 10, pp. 6740-6753, Oct. 2024.
[15] Y. Zhang, G. Ding, D. Ding*, Z. Ma, and Z. Li, "On content-aware post-processing: Adapting statistically learned models to dynamic content," ACM TOMM, vol. 20, no. 1, pp. 1-28, Jan. 2024.
[16] W. Wang, G. Ding, and D. Ding*, "Leveraging occupancy map to accelerate video-based point cloud compression," JVCI, vol. 96, p. 104292, Oct. 2024.
[17] D. Ding, J. Wang, G. Zhen, D. Mukherjee, U. Joshi, and Z. Ma, "Neural adaptive loop filtering for video coding: Exploring multi-hypothesis sample refinement," IEEE TCSVT, vol. 33, no. 8, pp. 3785-3799, Aug. 2023. [Adopted in AOM Software Model]
[18] G. Ding, X. Lin, J. Wang, and D. Ding*, "Accelerating QTMT-based CU partition and intra mode decision for versatile video coding," JVCI, vol. 89, p. 103832, 2023.
[19] J. Wang, D. Ding, Z. Li, X. Feng, C. Cao, and Z. Ma, "Sparse tensor-based multiscale representation for point cloud geometry compression," IEEE TPAMI, vol. 45, no. 12, pp. 14567-14581, Dec. 2023.
[20] D. Ding#, Z. Ma#, D. Chen, Q. Chen, Z. Liu, and F. Zhu, "Advances in video compression system using deep neural network: A review and case studies," Proceedings of the IEEE, vol. 109, no. 9, pp. 1494-1520, Sep. 2021. [该期刊首篇AI编码综述]
[21] D. Ding*, X. Gao, C. Tang, and Z. Ma, "Neural reference synthesis for inter frame coding," IEEE TIP, vol. 31, pp. 773-787, 2022.
[22] D. Ding, W. Wang, X. Gao, Z. Liu, and Y. Fang, "Bi-prediction based video quality enhancement via learning," IEEE TCYB, vol. 52, no. 2, pp. 1207-1220, Feb. 2022. [杭州师范大学2022自然科学学术成果奖]
[23] M. Lu, T. Chen, Z. Dai, D. Wang, D. Ding, and Z. Ma, "Decoder-side cross resolution synthesis for video compression enhancement," IEEE TMM, vol. 24, pp. 4215-4227, 2022.
[24] D. Ding, C. Qiu, F. Liu, and Z. Pan, "Point cloud upsampling via perturbation learning," IEEE TCSVT, vol. 31, no. 12, pp. 4661-4672, Dec. 2021.
[25] D. Ding, L. Kong, G. Chen, Z. Liu, and Y. Fang, "A switchable deep learning approach for in-loop filtering in video coding," IEEE TCSVT, vol. 30, no. 7, pp. 1871-1887, Jul. 2020.
近期发表学术会议论文：
[1] K. Mao, D. Ding, U. Joshi, and D. Mukherjee, "Adaptive AV2 in-loop filtering via guided neural model with vectorized quantization," IEEE ISCAS, 2026. [CCF C]
[2] J. Zhang, C. Han, D. Ding, and Z. Ma, "GeoQE: Enhancing quality of experience in point cloud streaming," ACM MM, pp. 6820–6829, Oct. 2025. [CCF A]
[3] J. Zhu, K. You, D. Ding, and Z. Ma, "Efficient LiDAR reflectance compression via scanning serialization," ICML, Jul. 2025. [CCF A]
[4] K. You, T. Chen, D. Ding, M. S. Asif, and Z. Ma, "Reno: Real-time neural compression for 3D LiDAR point clouds," CVPR, pp. 22172–22181, 2025. [CCF A]
[5] X. Bian, W. Wang, and D. Ding, "Super resolution-based video coding via lightweight implicit neural modeling," IEEE DCC, Snowbird, UT, USA, 2025. [CCF B]
[6] J. Zhang, T. Chen, H. Zhu, D. Wang, D. Ding, and Z. Ma, "Compressing 3D Gaussian splatting via a generalizable neural coder," IEEE VCIP, Tokyo, Japan, Dec. 2024.
[7] W. Wang, J. Wang, and D. Ding, "ELIM: Extremely low-complexity implicit neural model for super resolution-based coding," IEEE PCS, Taichung, Taiwan, Jun. 2024. [Best Paper Award Finalists]
[8] G. Liu, J. Zhu, D. Ding, and Z. Ma, "Encoding auxiliary information to restore compressed point cloud geometry," IJCAI, Jeju, South Korea, Aug. 2024. [CCF A]
[9] Y. Zhang, Z. Duan, M. Lu, D. Ding, F. Zhu, and Z. Ma, "Another way to the top: Exploit contextual clustering in learned image coding," AAAI, Vancouver, Canada, Feb. 2024. [CCF A]
[10] J. Zhang, T. Chen, D. Ding, and Z. Ma, "YOGA: Yet another geometry-based point cloud compressor," ACM MM, pp. 9070–9081, Ottawa, Canada, Oct. 2023. [CCF A]
[11] J. Zhang, T. Chen, D. Ding, and Z. Ma, "G-PCC++: Enhanced geometry-based point cloud compression," ACM MM, pp. 1352–1363, Ottawa, Canada, Oct. 2023. [CCF A]
[12] Y. Zhang, H. Liu, and D. Ding, "Low light raw image enhancement using paired fast Fourier convolution and transformer," IEEE VCIP, Suzhou, China, Dec. 2022.
[13] G. Liu, J. Wang, D. Ding, and Z. Ma, "PCGFormer: Lossy point cloud geometry compression via local self-attention," IEEE VCIP, Suzhou, China, Dec. 2022.
[14] J. Wang, G. Ding, D. Ding, D. Mukherjee, U. Joshi, and Y. Chen, "Quadtree-based guided CNN for AV1 in-loop filtering," IEEE ICIP, pp. 3331–3335, Bordeaux, France, Oct. 2022. [CCF C]
[15] L. Kong, D. Ding, D. Mukherjee, U. Joshi, and Y. Chen, "Guided CNN restoration with explicitly signaled linear combination," IEEE ICIP, Abu Dhabi, United Arab Emirates, Oct. 2020. [CCF C, Adopted in AOM Software Model]
八、发明专利及转化
[1] 一种用于视频编码帧间环路滤波的模型训练方法和使用方法（已转化）
[2] 一种用于视频编码的参考帧选择方法及装置（已转化）
[3] 一种基于多残差联合学习的水下图像增强方法（已授权）
[4] 一种视频编码方法（已授权）
[5] 一种视频处理方法（已授权）
[6] 一种基于神经网络的低光图像质量增强装置和方法
[7] 一种用于加快视频编码的编码单元划分方法及装置
[8] 一种基于点的点云几何有损压缩重建装置与方法
[9] 基于Transformer的点云几何压缩装置及方法
[10] 一种用于增强压缩点云重建质量的装置及方法