跳到主要导航 跳到搜索 跳到主要内容

HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation

  • Hefei University of Technology
  • Tencent
  • Tsinghua University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

22 引用 (Scopus)

摘要

2D-to-3D human pose lifting is fundamental for 3D human pose estimation (HPE), for which graph convolutional networks (GCNs) have proven inherently suitable for modeling the human skeletal topology. However, the current GCN-based 3D HPE methods update the node features by aggregating their neighbors' information without considering the interaction of joints in different joint synergies. Although some studies have proposed importing limb information to learn the movement patterns, the latent synergies among joints, such as maintaining balance are seldom investigated. We propose the Hop-wise GraphFormer with Intragroup Joint Refinement (HopFIR) architecture to tackle the 3D HPE problem. HopFIR mainly consists of a novel hop-wise GraphFormer (HGF) module and an intragroup joint refinement (IJR) module. The HGF module groups the joints by k-hop neighbors and applies a hop-wise transformer-like attention mechanism to these groups to discover latent joint synergies. The IJR module leverages the prior limb information for peripheral joint refinement. Extensive experimental results show that HopFIR outperforms the SOTA methods by a large margin, with a mean per-joint position error (MPJPE) on the Human3.6M dataset of 32.67 mm. We also demonstrate that the state-of-the-art GCN-based methods can benefit from the proposed hop-wise attention mechanism with a significant improvement in performance: SemGCN [42] and MGCN [49] are improved by 8.9% and 4.5%, respectively.

源语言英语
主期刊名Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
出版商Institute of Electrical and Electronics Engineers Inc.
页14939-14949
页数11
ISBN(电子版)9798350307184
DOI
出版状态已出版 - 2023
已对外发布是
活动2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, 法国
期限: 2 10月 2023 → 6 10月 2023

丛书

姓名Proceedings of the IEEE International Conference on Computer Vision
ISSN(印刷版)1550-5499

会议

会议2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
国家/地区法国
市Paris
时期2/10/23 → 6/10/23

学术指纹

探究 'HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation' 的科研主题。它们共同构成独一无二的学术指纹。

引用此