</> Code with Papers by Syntology

Papers › HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation

HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation

26 Oct 2019ICCV 2019 10arXiv:1910.12032archive 2025-07-28

Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu

Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing an intermediate state - Part-Centric Heatmap Triplets (HEMlets), which shortens the gap between the 2D observation and the 3D interpretation. The HEMlets utilize three joint-heatmaps to represent the relative depth information of the end-joints for each skeletal body part. In our approach, a Convolutional Network (ConvNet) is first trained to predict HEMlests from the input image, followed by a volumetric joint-heatmap regression. We leverage on the integral operation to extract the joint locations from the volumetric heatmaps, guaranteeing end-to-end learning. Despite the simplicity of the network design, the quantitative comparisons show a significant performance improvement over the best-of-grade method (by 20% on Human3.6M). The proposed method naturally supports training with "in-the-wild" images, where only weakly-annotated relative depth information of skeletal joints is available. This further improves the generalization ability of our model, as validated by qualitative comparisons on outdoor images.

PaperPDFConference PDF

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 EstimationMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M HEMlets Pose Average MPJPE (mm) 45.1 #44 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M HEMlets Pose Multi-View or Monocular Monocular #44 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M HEMlets Pose Using 2D ground-truth joints No #44 of 88 Archive leaderboard report
3D Human Pose Estimation HumanEva-I HEMlets Pose Mean Reconstruction Error (mm) 15.2 #5 of 31 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP HEMlets Pose AUC 38 #98 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP HEMlets Pose PCK 75.3 #98 of 108 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HEMlets Pose (H36M+MPII) Average MPJPE (mm) 39.9 #8 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HEMlets Pose (H36M+MPII) Frames Needed 1 #8 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HEMlets Pose (H36M+MPII) PA-MPJPE 27.9 #8 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HEMlets Pose Frames Needed 1 #48 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HEMlets Pose Need Ground Truth 2D Pose No #48 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HEMlets Pose Use Video Sequence No #48 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.

Methods

Heatmap

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