Papers › VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation

VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation

25 May 2022arXiv:2205.12602archive 2025-07-28

Yuxing Chen, Renshu Gu, Ouhan Huang, Gangyong Jia

This paper presents Volumetric Transformer Pose estimator (VTP), the first 3D volumetric transformer framework for multi-view multi-person 3D human pose estimation. VTP aggregates features from 2D keypoints in all camera views and directly learns the spatial relationships in the 3D voxel space in an end-to-end fashion. The aggregated 3D features are passed through 3D convolutions before being flattened into sequential embeddings and fed into a transformer. A residual structure is designed to further improve the performance. In addition, the sparse Sinkhorn attention is empowered to reduce the memory cost, which is a major bottleneck for volumetric representations, while also achieving excellent performance. The output of the transformer is again concatenated with 3D convolutional features by a residual design. The proposed VTP framework integrates the high performance of the transformer with volumetric representations, which can be used as a good alternative to the convolutional backbones. Experiments on the Shelf, Campus and CMU Panoptic benchmarks show promising results in terms of both Mean Per Joint Position Error (MPJPE) and Percentage of Correctly estimated Parts (PCP). Our code will be available.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose Estimation 3D Multi-Person Pose Estimation 3D Pose Estimation Pose Estimation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Human Pose Estimation	Panoptic	VTP	Average MPJPE (mm)	17.62	#4 of 9	Archive leaderboard	report
3D Multi-Person Pose Estimation	Campus	VTP	Mean mAP	80.1	#12 of 16	Archive leaderboard	report
3D Multi-Person Pose Estimation	Campus	VTP	PCP3D	96.3	#12 of 16	Archive leaderboard	report
3D Multi-Person Pose Estimation	Shelf	VTP	MPJPE	56.3	#15 of 27	Archive leaderboard	report
3D Multi-Person Pose Estimation	Shelf	VTP	PCP3D	97.3	#15 of 27	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Feedforward Network Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer ReLU Residual Connection Softmax Sparse Sinkhorn Attention Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections