Skip to main navigation Skip to search Skip to main content

FasterVoxelPose+: Fast and Accurate Voxel-based 3D Human Pose Estimation by Depth-wise Projection Decay

  • Zonghuang Zhuang
  • , Yue Zhou*
  • *Corresponding author for this work
  • Shanghai Jiao Tong University

Research output: Contribution to journal › Conference article › peer-review

Abstract

In terms of multi-person multi-view 3D pose estimation, voxel-based methods gain promising accuracy by directly manipulating features in 3D space. Since their high computational cost prevents them from practical applications, Faster VoxelPose was proposed to address this complication by re-projecting the 3D feature volume onto coordinate planes, which greatly improved the efficiency of the model. However, it suffers from an obvious performance drop, especially when there are fewer cameras. In this paper, we propose a more accurate real-time 3D pose estimation method, FasterVoxelPose+, to address the above problem. We have made two improvements to the previous methods. First, we propose a novel method for constructing voxel feature volume called Depth-wise Projection Decay (DPD). It introduces extra depth information to the projection to alleviate depth ambiguity. Second, we design an Encoder-Decoder Network for processing the re-projected voxel features to further push up the performance of the model. Our method obtains 17.42mm MPJPE on Panoptic with real-time speed and can be easily used in other voxel-based models.

Original languageEnglish
Pages (from-to)1763-1778
Number of pages16
JournalProceedings of Machine Learning Research
Volume222
StatePublished - 2023
Externally publishedYes
Event15th Asian Conference on Machine Learning, ACML 2023 - Istanbul, Turkey
Duration: 11 Nov 2023 → 14 Nov 2023

Keywords

  • Human Pose Estimation
  • Multi-view
  • Real-time
  • Voxel

Fingerprint

Dive into the research topics of 'FasterVoxelPose+: Fast and Accurate Voxel-based 3D Human Pose Estimation by Depth-wise Projection Decay'. Together they form a unique fingerprint.

Cite this