Papers › Mesh Graphormer

Mesh Graphormer

1 Apr 2021ICCV 2021 10arXiv:2104.00272archive 2025-07-28

Kevin Lin, Lijuan Wang, Zicheng Liu

We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image. Recently both transformers and graph convolutional neural networks (GCNNs) have shown promising progress in human mesh reconstruction. Transformer-based approaches are effective in modeling non-local interactions among 3D mesh vertices and body joints, whereas GCNNs are good at exploiting neighborhood vertex interactions based on a pre-specified mesh topology. In this paper, we study how to combine graph convolutions and self-attentions in a transformer to model both local and global interactions. Experimental results show that our proposed method, Mesh Graphormer, significantly outperforms the previous state-of-the-art methods on multiple benchmarks, including Human3.6M, 3DPW, and FreiHAND datasets. Code and pre-trained models are available at https://github.com/microsoft/MeshGraphormer

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

microsoft/meshgraphormer officialmentioned in papermentioned on GitHub report
MS-P3/code5 mindspore 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 Hand Pose Estimation3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation FreiHAND MeshGraphormer PA-F@15mm 0.986 #9 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MeshGraphormer PA-F@5mm 0.764 #9 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MeshGraphormer PA-MPJPE 5.9 #9 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MeshGraphormer PA-MPVPE 6.0 #9 of 33 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (Ego4D) All 14.6 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (Ego4D) Occ 8.3 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (Ego4D) Visible 18.4 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (New Days) All 16.8 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (NewDays) Occ 7.9 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (NewDays) Visible 22.3 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (VISOR) All 19.1 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (VISOR) Occ 10.9 #6 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild MeshGraphormer PCK@0.05 (VISOR) Visible 23.6 #6 of 10 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