Papers › GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras

GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras

2 Dec 2021CVPR 2022 1arXiv:2112.01524archive 2025-07-28

Ye Yuan, Umar Iqbal, Pavlo Molchanov, Kris Kitani, Jan Kautz

We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of view. To achieve this, we first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. Additionally, in contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras. Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements. Using the predicted trajectories as anchors, we present a global optimization framework that refines the predicted trajectories and optimizes the camera poses to match the video evidence such as 2D keypoints. Experiments on challenging indoor and in-the-wild datasets with dynamic cameras demonstrate that the proposed approach outperforms prior methods significantly in terms of motion infilling and global mesh recovery.

PaperPDFConference PDFCode

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

Code

nvlabs/glamr officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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 EstimationGlobal 3D Human Pose EstimationHuman Mesh Recoveryglobal-optimization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation EMDB GLAMR Average MPJAE (deg) 25.5058 #8 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB GLAMR Average MPJAE-PA (deg) 23.5484 #8 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB GLAMR Average MPJPE (mm) 107.797 #8 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB GLAMR Average MPJPE-PA (mm) 71.0091 #8 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB GLAMR Average MVE (mm) 128.237 #8 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB GLAMR Average MVE-PA (mm) 85.4586 #8 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB GLAMR Jitter (10m/s^3) 67.3522 #8 of 13 Archive leaderboard report
Global 3D Human Pose Estimation EMDB GLAMR Average G-MPJPE (mm) 3193 #1 of 1 Archive leaderboard report
Global 3D Human Pose Estimation EMDB GLAMR Average G-MVE (mm) 3203 #1 of 1 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