</> Code with Papers by Syntology

Papers › Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

8 Apr 2017ICCV 2017 10arXiv:1704.02447archive 2025-07-28

Xingyi Zhou, Qi-Xing Huang, Xiao Sun, xiangyang xue, Yichen Wei

In this paper, we study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure. Our network augments a state-of-the-art 2D pose estimation sub-network with a 3D depth regression sub-network. Unlike previous two stage approaches that train the two sub-networks sequentially and separately, our training is end-to-end and fully exploits the correlation between the 2D pose and depth estimation sub-tasks. The deep features are better learnt through shared representations. In doing so, the 3D pose labels in controlled lab environments are transferred to in the wild images. In addition, we introduce a 3D geometric constraint to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels. Our method achieves competitive results on both 2D and 3D benchmarks.

PaperPDFConference PDFCode

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

Code

xingyizhou/pose-hg-3d officialmentioned in papermentioned on GitHubpytorch report
ECE740F21T01/pytorch-pose-hg-3d mentioned on GitHubpytorch report
mengyingfei/pose-3d-pytorch-ros mentioned on GitHubpytorch report
mikeshihyaolin/pose-hg-3d-preprocessing mentioned on GitHub report
nish-97v/3D-human-pose-estimation mentioned on GitHubpytorch report
xingyizhou/pytorch-pose-hg-3d mentioned on GitHubpytorch 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

2D Pose Estimation3D Human Pose Estimation3D Multi-Person Pose Estimation (absolute)3D Multi-Person Pose Estimation (root-relative)Monocular 3D Human Pose EstimationPose EstimationPose PredictionTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Geometric Pose Affordance Baseline model MPJPE (CA) 89.2 #1 of 1 Archive leaderboard report
3D Human Pose Estimation Geometric Pose Affordance Baseline model MPJPE (CS) 99.4 #1 of 1 Archive leaderboard report
3D Human Pose Estimation Geometric Pose Affordance Baseline model PCK3D (CA) 83.6 #1 of 1 Archive leaderboard report
3D Human Pose Estimation Geometric Pose Affordance Baseline model PCK3D (CS) 81.3 #1 of 1 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Weakly Supervised Transfer Learning Average MPJPE (mm) 64.9 #34 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Weakly Supervised Transfer Learning Frames Needed 1 #34 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Weakly Supervised Transfer Learning Need Ground Truth 2D Pose No #34 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Weakly Supervised Transfer Learning Use Video Sequence No #34 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