一、导师基本情况

姓名：丁丹丹 副教授

邮箱：DandanDing@hznu.edu.cn, 187113186 (QQ)

指导专业：计算机科学与技术，电子信息等

课题组网站：https://github.com/3dpcc

二、研究领域

1. 多媒体通信、智能视频编码、三维点云编码与重建。

2. 多模态视觉感知、3DGS表征与生成、3D场景重建与理解。

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联合培养，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，主要从事多媒体通信、智能视频编码、三维点云压缩、三维重建与处理等研究工作。发表国内外高水平论文共60篇，包括TPAMI、Proceedings of the IEEE、TCyber、TIP、TVCG、TMM、TCSVT等TOP期刊，AAAI、ACM MM、IJCAI等CCF推荐A类会议及IEEE ISCAS、IEEE ICIP、IEEE DCC等领域知名学术会议。承担了国家自然科学基金面上项目、教育部博士点基金、省自然科学基金在内的多项国家和省部级项目，与Google公司、阿里巴巴、海康等企业有持续紧密合作。

申请发明专利30余项，向国内外标准组织提交提案40项。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组织AVS第13部分专题组联合组长，目前担任中国面向机器视觉编码工作组（DCM）点云组召集人。担任IEEE Signal Processing Letters期刊Associate Editor。

六、主持教学科研项目

[1] 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.

[2] 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.

[3] 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

[4] 阿里巴巴公司合作项目，视频编码的快速算法与码率控制算法研究，2024.3-2026.3

七、代表性论著（#共同作者，*通信作者）

近期发表期刊论文：

[1] Junzhe Zhang, Tong Chen, Kang You, Dandan Ding*, and Zhan Ma, ConPCAC: Conditional Lossless Point Cloud Attribute Compression via Spatial Decomposition, IEEE TCSVT, Feb. 2025.

[2] Junzhe Zhang, Gexin Liu, Junteng Zhang, Dandan Ding*, and Zhan Ma, DeepPCC: Learned Lossy Point Cloud Compression, IEEE TETCI, early access, Sept. 2024.

[3] Junteng Zhang, Junzhe Zhang, Wenxi Ma, Dandan Ding*, and Zhan Ma, Content-aware Rate Control for Geometry-based Point Cloud Compression, IEEE TCSVT, 2024, 34(10): 9550-9561.

[4] Junteng Zhang, Junzhe Zhang, Dandan Ding*, Zhan Ma, Learning to Restore Compressed Point Cloud Attribute: A Fully Data-Driven Approach and A Rules-Unrolling-Based Optimization, IEEE TVCG, early access, 2024.

[5] Gexin Liu, Ruixiang Xue, Jiaxin Li, Dandan Ding*, and Zhan Ma, GRNet: Geometry Restoration for G-PCC Compressed Point Clouds Using Auxiliary Density Signaling, IEEE TVCG, 2024, 30(10): 6740-6753.

[6] Junteng Zhang, Jianqiang Wang, Dandan Ding*, and Zhan Ma, Scalable Point Cloud Attribute Compression, IEEE TMM, early access, Nov. 2023.

[7] Dandan Ding, Junjie Wang, Guangkun Zhen, Debargha Mukherjee, Urvang Joshi, Zhan Ma, Neural Adaptive Loop Filtering For Video Coding: Exploring Multi-hypothesis Sample Refinement, IEEE TCSVT, 2023, 33(10): 6057-6071. [Adopted in AOM Software Model]

[8] Jianqiang Wang, Dandan Ding, Zhu Li, Xiaoxing Feng, Chuntong Cao, Zhan Ma, Sparse Tensor-Based Multiscale Representation for Point Cloud Geometry Compression, IEEE TPAMI, 2022, 45(7): 9055–9071. [Test Model in MPEG]

[9] Dandan Ding*, Xiang Gao, Chenran Tang, Zhan Ma, Neural Reference Synthesis for Inter Frame Coding, IEEE TIP, 2022, 31: 773-787.

[10] Dandan Ding, Wenyu Wang, Xinbo Gao, Zoe Liu, and Yong Fang*, Bi-Prediction Based Video Quality Enhancement via Learning, IEEE TCyber, 2022, 52(2): 1207-1220. [杭州师范大学2022自然科学学术成果奖]

[11] Dandan Ding#, Zhan Ma, Di Chen, Qingshuang Chen, Zoe Liu, and Fengqing Zhu*, Advances In Video Compression System Using Deep Neural Network: A Review And Case Studies, Proceedings of the IEEE, 2021, 109(9): 1494-1520. [该期刊首个AI编码综述]

[12] Dandan Ding, Chi Qiu, Fuchang Liu, Zhigeng Pan*, Point Cloud Upsampling via Perturbation Learning, IEEE TCSVT, 2021, 31(12): 4661-4672.

[13] Dandan Ding, Lingyi Kong, Guangyao Chen, Zoe Liu, and Yong Fang*, A Switchable Deep Learning Approach for In-loop Filtering in Video Coding, IEEE TCSVT, 2019, 30(7): 1871-1887.

近期发表学术会议论文：

[1] Xianlu Bian, Wenyu Wang, Dandan Ding*, Super Resolution-based Video Coding via Lightweight Implicit Neural Modeling, IEEE DCC, Snowbird, UT, USA, 2025.

[2] Junteng Zhang, Tong Chen, Hao Zhu, Dong Wang, Dandan Ding, and Zhan Ma, Compressing 3D Gaussian Splatting via a Generalizable Neural Coder, IEEE VCIP, Tokyo, Japan, Dec. 2024.

[3] Wenyu Wang, Junjie Wang, Dandan Ding*, ELIM: Extremely Low-Complexity Implicit Neural Model for Super Resolution-Based Coding, IEEE PCS, Taichung, Taiwan, June 2024. [Best Paper Award Finalists]

[4] Gexin Liu, Jiahao Zhu, Dandan Ding*, and Zhan Ma, Encoding Auxiliary Information to Restore Compressed Point Cloud Geometry, IJCAI, Jeju, South Korea, Aug. 2024.

[5] Yichi Zhang, Zhihao Duan, Ming Lu, Dandan Ding*, Fengqing Zhu, Zhan Ma, Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding, AAAI, Vancouver, Canada, Feb. 2024.

[6] Junteng Zhang, Tong Chen, Dandan Ding*, and Zhan Ma, YOGA: Yet Another Geometry-based Point Cloud Compressor, ACM MM, pp. 9070-9081, Ottawa, Canada, Oct. 2023.

[7] Junzhe Zhang, Tong Chen, Dandan Ding*, and Zhan Ma, G-PCC++: Enhanced Geometry-based Point Cloud Compression, ACM MM, pp. 1352-1363, Ottawa, Canada, Oct. 2023.

[8] Yichi Zhang, Hengyu Liu, Dandan Ding*, Zhan Ma, Low light raw image enhancement using paired fast fourier convolution and transformer, IEEE VCIP, Suzhou, China, Dec. 2022.

[9] Gexin Liu, Jianqiang Wang, Dandan Ding*, Zhan Ma, PCGFormer: Lossy Point Cloud Geometry Compression via Local Self-Attention, IEEE VCIP, Suzhou, China, Dec. 2022.

[10] Junjie Wang, Gongchun Ding, Dandan Ding*, Debargha Mukherjee, Urvang Joshi, Yue Chen, Quadtree-based Guided CNN for AV1 In-loop Filtering, IEEE ICIP, pp. 3331-3335, Bordeaux, France, Oct. 2022.

[11] Lingyi Kong, Dandan Ding*, Debargha Mukherjee, Urvang Joshi, Yue Chen, Guided CNN Restoration with Explicitly Signaled Linear Combination, IEEE ICIP, Abu Dhabi, United Arab Emirates, Oct. 2020. [Adopted in AOM Software Model]

[12] Junchao Tong, Xilin Wu, Dandan Ding*, Zheng Zhu, and Zoe Liu, Learning-Based Multi-frame Video Quality Enhancement, IEEE ICIP, Taipei, Taiwan, Sept. 2019.

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