Papers › Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation

Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation

7 Apr 2020arXiv:2004.03143archive 2025-07-28

Zhe Wang, Daeyun Shin, Charless C. Fowlkes

Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent methods generalize outside the specific datasets they are trained on. In this work we carry out a systematic study of the diversity and biases present in specific datasets and its effect on cross-dataset generalization across a compendium of 5 pose datasets. We specifically focus on systematic differences in the distribution of camera viewpoints relative to a body-centered coordinate frame. Based on this observation, we propose an auxiliary task of predicting the camera viewpoint in addition to pose. We find that models trained to jointly predict viewpoint and pose systematically show significantly improved cross-dataset generalization.

PaperPDF

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 EstimationDiversityMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Geometric Pose Affordance Cross Dataset Generalization MPJPE 53.3 #2 of 2 Archive leaderboard report
3D Human Pose Estimation Surreal Cross Dataset Generalization MPJPE 37.1 #2 of 6 Archive leaderboard report
3D Human Pose Estimation Surreal Cross Dataset Generalization PCK 97.3 #2 of 6 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M cross-dataset-evaluation Average MPJPE (mm) 52.0 #25 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M cross-dataset-evaluation Frames Needed 1 #25 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M cross-dataset-evaluation Need Ground Truth 2D Pose No #25 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M cross-dataset-evaluation Use Video Sequence No #25 of 52 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