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
  • [41] Monocular 3D Human Pose Markerless Systems for Gait Assessment
    Zhu, Xuqi
    Boukhennoufa, Issam
    Liew, Bernard
    Gao, Cong
    Yu, Wangyang
    McDonald-Maier, Klaus D.
    Zhai, Xiaojun
    BIOENGINEERING-BASEL, 2023, 10 (06):
  • [42] Staged cascaded network for monocular 3D human pose estimation
    Gao, Bing-kun
    Zhang, Zhong-xin
    Wu, Cui-na
    Wu, Chen-lei
    Bi, Hong-bo
    APPLIED INTELLIGENCE, 2023, 53 (01) : 1021 - 1029
  • [43] Chasing the Tail in Monocular 3D Human Reconstruction With Prototype Memory
    Rong, Yu
    Liu, Ziwei
    Loy, Chen Change
    IEEE Transactions on Image Processing, 2022, 31 : 2907 - 2919
  • [44] 3D HUMAN MODEL ACQUISITION FROM UNCALIBRATED MONOCULAR VIDEO
    Peng, En
    Li, Ling
    COMPUTER VISION AND GRAPHICS (ICCVG 2004), 2006, 32 : 1018 - 1023
  • [45] 3D Reconstruction of Human Motion from Monocular Image Sequences
    Wandt, Bastian
    Ackermann, Hanno
    Rosenhahn, Bodo
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (08) : 1505 - 1516
  • [46] TSwinPose: Enhanced monocular 3D human pose estimation with JointFlow
    Li, Muyu
    Hu, Henan
    Xiong, Jingjing
    Zhao, Xudong
    Yan, Hong
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 249
  • [47] LEARNING MONOCULAR 3D HUMAN POSE ESTIMATION WITH SKELETAL INTERPOLATION
    Chen, Ziyi
    Sugimoto, Akihiro
    Lai, Shang-Hong
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 4218 - 4222
  • [48] Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows
    Wehrbein, Tom
    Rudolph, Marco
    Rosenhahn, Bodo
    Wandt, Bastian
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 11179 - 11188
  • [49] Recovery of 3D Human Posture based on Monocular Vision Technology
    Zhang, Xiao
    Huang, Qiang
    2009 IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND INTELLIGENT SYSTEMS, PROCEEDINGS, VOL 4, 2009, : 5 - 8
  • [50] Markerless 3D human motion tracking for monocular video sequences
    Zou, Beiji
    Chen, Shu
    Peng, Xiaoning
    Shi, Cao
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2008, 20 (08): : 1047 - 1055