DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model

被引:7
作者
Choi, Jeongjun [1 ,2 ]
Shim, Dongseok [1 ]
Kim, H. Jin [1 ,2 ]
机构
[1] Seoul Natl Univ, Artificial Intelligence Inst AIIS, Seoul, South Korea
[2] Automat & Syst Res Inst ASRI, Seoul, South Korea
来源
2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, IROS | 2023年
基金
新加坡国家研究基金会;
关键词
D O I
10.1109/IROS55552.2023.10342204
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth ambiguities and occlusions. To handle this problem, many previous works exploit temporal information to mitigate such difficulties. However, there are many real-world applications where frame sequences are not accessible. This paper focuses on reconstructing a 3D pose from a single 2D keypoint detection. Rather than exploiting temporal information, we alleviate the depth ambiguity by generating multiple 3D pose candidates which can be mapped to an identical 2D keypoint. We build a novel diffusion-based framework to effectively sample diverse 3D poses from an off-the-shelf 2D detector. By considering the correlation between human joints by replacing the conventional denoising U-Net with graph convolutional network, our approach accomplishes further performance improvements. We evaluate our method on the widely adopted Human3.6M and HumanEva-I datasets. Comprehensive experiments are conducted to prove the efficacy of the proposed method, and they confirm that our model outperforms state-of-the-art multi-hypothesis 3D HPE methods.
引用
收藏
页码:3773 / 3780
页数:8
相关论文
共 48 条
  • [1] Recovering 3D human pose from monocular images
    Agarwal, A
    Triggs, B
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (01) : 44 - 58
  • [2] [Anonymous], 2020, EUR C COMP VIS, DOI DOI 10.5220/0008880403310338
  • [3] [Anonymous], 2022, P IEEE CVF C COMP VI, DOI DOI 10.1109/ITC50671.2022.00083
  • [4] Bishop C. M., 1994, MIXTURE DENSITY NETW
  • [5] Exploiting Spatial-temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks
    Cai, Yujun
    Ge, Liuhao
    Liu, Jun
    Cai, Jianfei
    Cham, Tat-Jen
    Yuan, Junsong
    Thalmann, Nadia Magnenat
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 2272 - 2281
  • [6] Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
    Cao, Zhe
    Simon, Tomas
    Wei, Shih-En
    Sheikh, Yaser
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1302 - 1310
  • [7] Chen Tianlang, 2021, IEEE T CIRCUITS SYST
  • [8] Cascaded Pyramid Network for Multi-Person Pose Estimation
    Chen, Yilun
    Wang, Zhicheng
    Peng, Yuxiang
    Zhang, Zhiqiang
    Yu, Gang
    Sun, Jian
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 7103 - 7112
  • [9] Optimizing Network Structure for 3D Human Pose Estimation
    Ci, Hai
    Wang, Chunyu
    Ma, Xiaoxuan
    Wang, Yizhou
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 2262 - 2271
  • [10] Clever HM, 2018, IEEE INT C INT ROBOT, P54, DOI 10.1109/IROS.2018.8593545