Papers › Learnable human mesh triangulation for 3D human pose and shape estimation

Learnable human mesh triangulation for 3D human pose and shape estimation

24 Aug 2022arXiv:2208.11251archive 2025-07-28

Sungho Chun, Sungbum Park, Ju Yong Chang

Compared to joint position, the accuracy of joint rotation and shape estimation has received relatively little attention in the skinned multi-person linear model (SMPL)-based human mesh reconstruction from multi-view images. The work in this field is broadly classified into two categories. The first approach performs joint estimation and then produces SMPL parameters by fitting SMPL to resultant joints. The second approach regresses SMPL parameters directly from the input images through a convolutional neural network (CNN)-based model. However, these approaches suffer from the lack of information for resolving the ambiguity of joint rotation and shape reconstruction and the difficulty of network learning. To solve the aforementioned problems, we propose a two-stage method. The proposed method first estimates the coordinates of mesh vertices through a CNN-based model from input images, and acquires SMPL parameters by fitting the SMPL model to the estimated vertices. Estimated mesh vertices provide sufficient information for determining joint rotation and shape, and are easier to learn than SMPL parameters. According to experiments using Human3.6M and MPI-INF-3DHP datasets, the proposed method significantly outperforms the previous works in terms of joint rotation and shape estimation, and achieves competitive performance in terms of joint location estimation.

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 Estimation3D human pose and shape estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M LMT R152 384x384 Angular Error 11.33 #1 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R152 384x384 Average MPJPE (mm) 17.59 #1 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R152 384x384 MPVE (mm) 23.7 #1 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R152 384x384 Multi-View or Monocular Multi-View #1 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R152 384x384 Using 2D ground-truth joints No #1 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R50 224x224 Angular Error 14.61 #9 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R50 224x224 Average MPJPE (mm) 30.56 #9 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R50 224x224 MPVE (mm) 42.28 #9 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R50 224x224 Multi-View or Monocular Multi-View #9 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M LMT R50 224x224 Using 2D ground-truth joints No #9 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP LMT R152 384x384 AUC 77.09 #16 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP LMT R152 384x384 MPJPE 33.7 #16 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP LMT R152 384x384 PCK 99.37 #16 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP (R50-224) LMT AUC 71.57 #19 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP (R50-224) LMT MPJPE 45.87 #19 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP (R50-224) LMT PCK 96.59 #19 of 108 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