研究领域:
三维视觉, 运动捕捉, 深度感知
教育与工作经历:
01/2022 – Present, 助理研究员/副研究 信息国研中心, 清华大学
12/2019 – 12/2021, 博士后,自动化系, 清华大学
10/2017 – 11/2019, 实习研究生, 自动化系, 清华大学
06/2017 – 09/2017, 研究助理, 前沿技术研究所, 南加州大学
09/2012 – 11/2019, 博士. 精密仪器及机械 北京航空航天大学
09/2008 – 07/2012, 本科. 仪器科学与光电工程学院, 合肥工业大学
近三年代表性成果(#共同一作,*共同通讯):
1、 Yitong Jin#; Zhiping Qiu#; Yi Shi; Shuangpeng Sun; Chongwu Wang; Donghao Pan; Jiachen Zhao; Zhenghao Liang; Yuan Wang; Xiaobing Li; Feng Yu; Tao Yu* and Qionghai Dai*; Audio Matters Too! Enhancing Markerless Motion Capture with Audio Signals for String Performance Capture, ACM Transaction on Graphics (TOG) & SIGGRAPH 2024.
2、 Haoxiang Wang, Tao Yu*, Tianwei Yang, Hui Qiao* and Qionghai Dai; Neural Physical Simulation with Multi-Resolution Hash Grid Encoding. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2024 Oral Presentation). 38, 6 (Mar. 2024), 5410-5418.
3、 Peng Li; Jiayin Zhao; Jingyao Wu; Chao Deng; Yuqi Han; Haoqian Wang* and Tao Yu*; OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE-TPAMI), 2023, 46(2): 681-694.
4、 Jiachen Zhao; Tao Yu*; Liang An; Yipeng Huang; Fang Deng; Qionghai Dai*; Triangulation Residual Loss for Data-efficient 3D Pose Estimation, Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans.
5、 Tao Yu; Zerong Zheng; Kaiwen Guo; Pengpeng Liu; Qionghai Dai and Yebin Liu; Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors, 34th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021 Oral Presentation), Online Virtual Conference.
研究方向:
主要开展三维视觉领域的前沿研究工作,专注于从微观到宏观等不同尺度场景的光场/辐射场重建以及从人类(用于数字内容创建和元宇宙)到动物(用于计算行为研究)等各种对象的精细化动作捕捉与行为分析。相关研究成果已技术授权多家知名公司,并应用于工业产品中。
荣誉与奖励:
2022 吴文俊人工智能科技进步二等奖