Idioma:

VoxelPose: Towards Multi-camera 3D Human Pose Estimation in Wild Environment

Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael

Computer Vision - ECCV 2020, 2020, Vol.12346, p.197-212 [Periódico revisado por pares]

Sem texto completo

Citações Citado por

Título:
VoxelPose: Towards Multi-camera 3D Human Pose Estimation in Wild Environment
Autor: Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael
Assuntos: 3D human pose estimation
É parte de: Computer Vision - ECCV 2020, 2020, Vol.12346, p.197-212
Notas: This work is done when Hanyue Tu is an intern at Microsoft Research Asia.
Descrição: We present VoxelPose to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimates, VoxelPose directly operates in the 3D space therefore avoids making incorrect decisions in each camera view. To achieve this goal, features in all camera views are aggregated in the 3D voxel space and fed into Cuboid Proposal Network (CPN) to localize all people. Then we propose Pose Regression Network (PRN) to estimate a detailed 3D pose for each proposal. The approach is robust to occlusion which occurs frequently in practice. Without bells and whistles, it outperforms the previous methods on several public datasets.
Títulos relacionados: Lecture Notes in Computer Science
Editor: Switzerland: Springer International Publishing AG
Idioma: Inglês

Voltar para lista de resultados