Lifting Monocular Events to 3D Human Poses

被引:9
|
作者
Scarpellini, Gianluca [1 ,2 ]
Morerio, Pietro [1 ]
Del Bue, Alessio [1 ,3 ]
机构
[1] Ist Italiano Tecnol, Pattern Anal & Comp Vis, Genoa, Italy
[2] Univ Genoa, Genoa, Italy
[3] Ist Italiano Tecnol, Visual Geometry & Modelling, Genoa, Italy
关键词
D O I
10.1109/CVPRW53098.2021.00150
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a novel 3D human pose estimation approach using a single stream of asynchronous events as input. Most of the state-of-the-art approaches solve this task with RGB cameras, however struggling when subjects are moving fast. On the other hand, event-based 3D pose estimation benefits from the advantages of event-cameras, especially their efficiency and robustness to appearance changes. Yet, finding human poses in asynchronous events is in general more challenging than standard RGB pose estimation, since little or no events are triggered in static scenes. Here we propose the first learning-based method for 3D human pose from a single stream of events. Our method consists of two steps. First, we process the event-camera stream to predict three orthogonal heatmaps per joint; each heatmap is the projection of of the joint onto one orthogonal plane. Next, we fuse the sets of heatmaps to estimate 3D localisation of the body joints. As a further contribution, we make available a new, challenging dataset for event-based human pose estimation by simulating events from the RGB Human3.6m dataset. Experiments demonstrate that our method achieves solid accuracy, narrowing the performance gap between standard RGB and event-based vision. The code is freely available at https://iit-pavis.github.io/lifting_events_to_3d_hpe.
引用
收藏
页码:1358 / 1368
页数:11
相关论文
共 50 条
  • [21] Recovering 3D human pose from monocular images
    Agarwal, A
    Triggs, B
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (01) : 44 - 58
  • [22] Pictorial Human Spaces: A Computational Study on the Human Perception of 3D Articulated Poses
    Marinoiu, Elisabeta
    Papava, Dragos
    Sminchisescu, Cristian
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2016, 119 (02) : 194 - 215
  • [23] Pictorial Human Spaces: A Computational Study on the Human Perception of 3D Articulated Poses
    Elisabeta Marinoiu
    Dragos Papava
    Cristian Sminchisescu
    International Journal of Computer Vision, 2016, 119 : 194 - 215
  • [24] Adapted human pose: monocular 3D human pose estimation with zero real 3D pose data
    Liu, Shuangjun
    Sehgal, Naveen
    Ostadabbas, Sarah
    APPLIED INTELLIGENCE, 2022, 52 (12) : 14491 - 14506
  • [25] Adapted human pose: monocular 3D human pose estimation with zero real 3D pose data
    Shuangjun Liu
    Naveen Sehgal
    Sarah Ostadabbas
    Applied Intelligence, 2022, 52 : 14491 - 14506
  • [26] Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept
    Nie, Qiang
    Liu, Ziwei
    Liu, Yunhui
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2023, 131 (05) : 1250 - 1268
  • [27] Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept
    Qiang Nie
    Ziwei Liu
    Yunhui Liu
    International Journal of Computer Vision, 2023, 131 : 1250 - 1268
  • [28] Forecasting of 3D Whole-body Human Poses with Grasping Objects
    Yan, Haitao
    Cui, Qiongjie
    Xie, Jiexin
    Guo, Shijie
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024, 2024, : 1726 - 1736
  • [29] Learning to Augment Poses for 3D Human Pose Estimation in Images and Videos
    Zhang, Jianfeng
    Gong, Kehong
    Wang, Xinchao
    Feng, Jiashi
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (08) : 10012 - 10026
  • [30] Recovering 3D Human Poses and Camera Motions from Deep Sequence
    Shimizu, Takashi
    Sakaue, Fumihiko
    Sato, Jun
    PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2018), VOL 5: VISAPP, 2018, : 393 - 398