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
  • [21] Precise 3D Pose Estimation of Human Faces
    Pernek, Akos
    Hajder, Levente
    [J]. PROCEEDINGS OF THE 2014 9TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, THEORY AND APPLICATIONS (VISAPP 2014), VOL 3, 2014, : 618 - 625
  • [23] Deep 3D human pose estimation: A review
    Wang, Jinbao
    Tan, Shujie
    Zhen, Xiantong
    Xu, Shuo
    Zheng, Feng
    He, Zhenyu
    Shao, Ling
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2021, 210
  • [24] 3D Human Pose Estimation With Adversarial Learning
    Meng, Wenming
    Hu, Tao
    Shuai, Li
    [J]. 2019 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND VISUALIZATION (ICVRV), 2019, : 93 - 99
  • [25] 3D human pose estimation by depth map
    Wu, Jianzhai
    Hu, Dewen
    Xiang, Fengtao
    Yuan, Xingsheng
    Su, Jiongming
    [J]. VISUAL COMPUTER, 2020, 36 (07): : 1401 - 1410
  • [26] View Invariant 3D Human Pose Estimation
    Wei, Guoqiang
    Lan, Cuiling
    Zeng, Wenjun
    Chen, Zhibo
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2020, 30 (12) : 4601 - 4610
  • [27] MONOCULAR 3D HUMAN POSE ESTIMATION BY CLASSIFICATION
    Greif, Thomas
    Lienhart, Rainer
    Sengupta, Debabrata
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2011,
  • [28] 3D human pose estimation by depth map
    Jianzhai Wu
    Dewen Hu
    Fengtao Xiang
    Xingsheng Yuan
    Jiongming Su
    [J]. The Visual Computer, 2020, 36 : 1401 - 1410
  • [29] Calibrated deep attention model for 3D pose estimation in the wild
    Jiang, Longkui
    Wang, Yuru
    Ji, Xinhe
    [J]. ELECTRONIC RESEARCH ARCHIVE, 2023, 31 (03): : 1556 - 1569
  • [30] In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations
    Habibie, Ikhsanul
    Xu, Weipeng
    Mehta, Dushyant
    Pons-Moll, Gerard
    Theobalt, Christian
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 10897 - 10906