Papers › VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimation

VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimation

24 Oct 2024arXiv:2410.18723archive 2025-07-28

Daniel Bermuth, Alexander Poeppel, Wolfgang Reif

In the rapidly evolving field of computer vision, the task of accurately estimating the poses of multiple individuals from various viewpoints presents a formidable challenge, especially if the estimations should be reliable as well. This work presents an extensive evaluation of the generalization capabilities of multi-view multi-person pose estimators to unseen datasets and presents a new algorithm with strong performance in this task. It also studies the improvements by additionally using depth information. Since the new approach can not only generalize well to unseen datasets, but also to different keypoints, the first multi-view multi-person whole-body estimator is presented. To support further research on those topics, all of the work is publicly accessible.

PaperPDFCode

Code

gitlab.com/Percipiote/VoxelKeypointFusion officialmentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

3D Human Pose EstimationMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M VoxelKeypointFusion (transfer) Average MPJPE (mm) 64.3 #86 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VoxelKeypointFusion (transfer) Multi-View or Monocular Multi-View #86 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VoxelKeypointFusion (transfer) Using 2D ground-truth joints No #86 of 88 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.

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