POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture

被引:17
|
作者
Li, Zhe [1 ]
Yu, Tao [1 ]
Zheng, Zerong [1 ]
Guo, Kaiwen [2 ]
Liu, Yebin [1 ]
机构
[1] Tsinghua Univ, Dept Automat, Beijing, Peoples R China
[2] Google, Zurich, Switzerland
基金
中国博士后科学基金;
关键词
MOTION CAPTURE;
D O I
10.1109/CVPR46437.2021.01394
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose POse-guided SElective Fusion (POSEFusion), a single-view human volumetric capture method that leverages tracking-based methods and tracking-free inference to achieve high-fidelity and dynamic 3D reconstruction. By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions. We formulate the keyframe selection as a dynamic programming problem to guarantee the temporal continuity of the reconstructed sequence. Moreover, the novel robust implicit surface fusion involves an adaptive blending weight to preserve high-fidelity surface details and an automatic collision handling method to deal with the potential self-collisions. Overall, our method enables high-fidelity and dynamic capture in both visible and invisible regions from a single RGBD camera, and the results and experiments show that our method outperforms state-of-the-art methods.
引用
收藏
页码:14157 / 14167
页数:11
相关论文
共 50 条
  • [1] Motion capture and human pose reconstruction from a single-view video sequence
    Gudukbay, Ugur
    Demir, Ibrahim
    Dedeoglu, Yigithan
    [J]. DIGITAL SIGNAL PROCESSING, 2013, 23 (05) : 1441 - 1450
  • [2] LEARNABLE MASKS FOR POSE-GUIDED VIEW SYNTHESIS
    Lakhal, Mohamed Ilyes
    Lanz, Oswald
    Cavallaro, Andrea
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 1775 - 1779
  • [3] Pose-Guided Human Animation from a Single Image in the Wild
    Yoon, Jae Shin
    Liu, Lingjie
    Golyanik, Vladislav
    Sarkar, Kripasindhu
    Park, Hyun Soo
    Theobalt, Christian
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 15034 - 15043
  • [4] Pose-Guided Human Image Synthesis Based on Fusion Feature Feedback Mechanism
    Huang Youwen
    Zhao Peng
    You Yadong
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (14)
  • [5] Consistent View Synthesis with Pose-Guided Diffusion Models
    Tseng, Hung-Yu
    Li, Qinbo
    Kim, Changil
    Alsisan, Suhib
    Huang, Jia-Bin
    Kopf, Johannes
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 16773 - 16783
  • [6] Appearance and Pose-guided Human Generation: A Survey
    Liao, Fangjian
    Zou, Xingxing
    Wong, Waikeung
    [J]. ACM COMPUTING SURVEYS, 2024, 56 (05)
  • [7] Human Body Pose Recognition from a Single-View Depth Camera
    Huang, Po-Chi
    Jeng, Shyh-Kang
    [J]. PROCEEDINGS 2012 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2012, : 2144 - 2149
  • [8] SimulCap : Single-View Human Performance Capture with Cloth Simulation
    Yu, Tao
    Zheng, Zerong
    Zhong, Yuan
    Zhao, Jianhui
    Dai, Qionghai
    Pons-Moll, Gerard
    Liu, Yebin
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 5499 - 5509
  • [9] POSE2BODY: POSE-GUIDED HUMAN PARTS SEGMENTATION
    Li, Zhong
    Chen, Xin
    Zhou, Wangyiteng
    Zhang, Yingliang
    Yu, Jingyi
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2019, : 640 - 645
  • [10] Pose-guided Generative Adversarial Net for Novel View Action Synthesis
    Li, Xianhang
    Zhang, Junhao
    Li, Kunchang
    Vyas, Shruti
    Rawat, Yogesh S.
    [J]. 2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 3103 - 3112