SMPLy Benchmarking 3D Human Pose Estimation in the Wild

被引:4
|
作者
Leroy, Vincent [1 ]
Weinzaepfel, Philippe [1 ]
Bregier, Romain [1 ]
Combaluzier, Hadrien [1 ]
Rogez, Gregory [1 ]
机构
[1] NAVER LABS Europe, Meylan, France
关键词
CAPTURE;
D O I
10.1109/3DV50981.2020.00040
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Predicting 3D human pose from images has seen great recent improvements. Novel approaches that can even predict both pose and shape from a single input image have been introduced, often relying on a parametric model of the human body such as SMPL. While qualitative results for such methods are often shown for images captured in-the-wild, a proper benchmark in such conditions is still missing, as it is cumbersome to obtain ground-truth 3D poses elsewhere than in a motion capture room. This paper presents a pipeline to easily produce and validate such a dataset with accurate ground-truth, with which we benchmark recent 3D human pose estimation methods in-the-wild. We make use of the recently introduced Mannequin Challenge dataset which contains in-the-wild videos of people frozen in action like statues and leverage the fact that people are static and the camera moving to accurately fit the SMPL model on the sequences. A total of 24,428 frames with registered body models are then selected from 567 scenes at almost no cost, using only online RGB videos. We benchmark state-of-the-art SMPL-based human pose estimation methods on this dataset. Our results highlight that challenges remain, in particular for difficult poses or for scenes where the persons are partially truncated or occluded.
引用
收藏
页码:301 / 310
页数:10
相关论文
共 50 条
  • [1] Generalizing Monocular 3D Human Pose Estimation in the Wild
    Wang, Luyang
    Chen, Yan
    Guo, Zhenhua
    Qian, Keyuan
    Lin, Mude
    Li, Hongsheng
    Ren, Jimmy S.
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 4024 - 4033
  • [2] 3D Human Pose Estimation in the Wild by Adversarial Learning
    Yang, Wei
    Ouyang, Wanli
    Wang, Xiaolong
    Ren, Jimmy
    Li, Hongsheng
    Wang, Xiaogang
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 5255 - 5264
  • [3] Benchmarking 3D pose estimation for face recognition
    Dou, Pengfei
    Wu, Yuhang
    Shah, Shishir K.
    Kakadiaris, Ioannis A.
    [J]. 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 190 - 195
  • [4] 3D Pose Estimation of Bats in the Wild
    Breslav, Mikhail
    Fuller, Nathan
    Sclaroff, Stan
    Betke, Margrit
    [J]. 2014 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2014, : 91 - 98
  • [5] Exploiting temporal context for 3D human pose estimation in the wild
    Arnab, Anurag
    Doersch, Carl
    Zisserman, Andrew
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 3390 - 3399
  • [6] 3D Pose Estimation and 3D Model Retrieval for Objects in the Wild
    Grabner, Alexander
    Roth, Peter M.
    Lepetit, Vincent
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 3022 - 3031
  • [7] Adapted human pose: monocular 3D human pose estimation with zero real 3D pose data
    Liu, Shuangjun
    Sehgal, Naveen
    Ostadabbas, Sarah
    [J]. APPLIED INTELLIGENCE, 2022, 52 (12) : 14491 - 14506
  • [8] Adapted human pose: monocular 3D human pose estimation with zero real 3D pose data
    Shuangjun Liu
    Naveen Sehgal
    Sarah Ostadabbas
    [J]. Applied Intelligence, 2022, 52 : 14491 - 14506
  • [9] Overview of 3D Human Pose Estimation
    Lin, Jianchu
    Li, Shuang
    Qin, Hong
    Wang, Hongchang
    Cui, Ning
    Jiang, Qian
    Jian, Haifang
    Wang, Gongming
    [J]. CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2023, 134 (03): : 1621 - 1651
  • [10] On the Robustness of 3D Human Pose Estimation
    Chen, Zerui
    Huang, Yan
    Wang, Liang
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 5326 - 5332