Papers › Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in...

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

22 Dec 2020arXiv:2012.11806archive 2025-07-28

Yu Cheng, Bo wang, Bo Yang, Robby T. Tan

Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and inaccurate person detection. To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters. In particular, we introduce a human-joint GCN, which, unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results. We also introduce a human-bone GCN, which models the bone connections and provides more information beyond human joints. The two GCNs work together to estimate the spatial frame-wise 3D poses and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information. To further refine the 3D pose estimation, we use our temporal convolutional networks (TCNs) to enforce the temporal and human-dynamics constraints. We use a joint-TCN to estimate person-centric 3D poses across frames, and propose a velocity-TCN to estimate the speed of 3D joints to ensure the consistency of the 3D pose estimation in consecutive frames. Finally, to estimate the 3D human poses for multiple persons, we propose a root-TCN that estimates camera-centric 3D poses without requiring camera parameters. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method.

PaperPDFCode

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

Code

3dpose/GnTCN officialmentioned in papermentioned on GitHubpytorchMIT 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 Absolute Human Pose Estimation3D Human Pose Estimation3D Multi-Person Pose Estimation3D Multi-Person Pose Estimation (absolute)3D Multi-Person Pose Estimation (root-relative)3D Pose EstimationMonocular 3D Human Pose EstimationMulti-Person Pose EstimationPose EstimationRoot Joint Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Absolute Human Pose Estimation Human3.6M GnTCN MRPE 88.1 #1 of 4 Archive leaderboard report
3D Human Pose Estimation 3DPW GnTCN PA-MPJPE 64.2 #98 of 119 Archive leaderboard report
3D Human Pose Estimation Human3.6M GnTCN Average MPJPE (mm) 40.9 #20 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M GnTCN Multi-View or Monocular Monocular #20 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M GnTCN PA-MPJPE 30.4 #20 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M GnTCN Using 2D ground-truth joints No #20 of 88 Archive leaderboard report
3D Multi-Person Pose Estimation (absolute) MuPoTS-3D GnTCN 3DPCK 45.7 #3 of 14 Archive leaderboard report
3D Multi-Person Pose Estimation (root-relative) MuPoTS-3D GnTCN 3DPCK 87.5 #3 of 20 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

GCNGraph Convolutional Networks

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