SGAT: Semantic Graph Attention for 3D human pose estimation

  • Luiz Schirmer PUC-Rio
  • Djalma Lucio PUC-Rio
  • Leandro Cruz University of Coimbra
  • Alberto Raposo PUC-Rio
  • Luiz Velho IMPA
  • Hélio Lopes PUC-Rio

Resumo


We propose a novel gating mechanism applied to Semantic Graph Convolutions for 3D applications, named Semantic Graph Attention. Semantic Graph Convolutions learn to capture semantic information such as local and global node relationships, not explicitly represented in graphs. We improve their performance by proposing an attention block to explore channel-wise inter-dependencies. The proposed method performs the unprojection of the 2D points (image) onto their 3D version. We use it to estimate 3d human pose from 2D images. Both 2D and 3D human poses can be represented as structured graphs, exploring their particularities in this context. The attention layer improves the accuracy of skeleton estimation using 58% fewer parameters than state-of-the-art.
Palavras-chave: Graphics, Three-dimensional displays, Semantics, Pose estimation, Skeleton, Graph Neural Networks, Pose Estimation, Animation, Motion Capture
Publicado
18/10/2021
SCHIRMER, Luiz; LUCIO, Djalma; CRUZ, Leandro; RAPOSO, Alberto; VELHO, Luiz; LOPES, Hélio. SGAT: Semantic Graph Attention for 3D human pose estimation. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 34. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 .