Research map / 3D vision / Human pose estimation
3D Human Mesh Estimation From Virtual Markers
Xiaoxuan Ma, Jiajun Su, Chunyu Wang, Wentao Zhu, Yizhou Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use learned virtual markers instead of skeleton joints (ablation) | Ours · H3.6M | MPVE: 64.4 -> 58.0 | Improved |
| Use learned virtual markers instead of skeleton joints (ablation) | Ours · SURREAL | MPVE: 53.6 -> 44.7 | Improved |
| Learn the virtual markers rather than selecting 64 vertices randomly (ablation) | Ours · H3.6M | MPVE: 63.0 -> 58.0 | Improved |
| Learn the virtual markers rather than selecting 64 vertices randomly (ablation) | Ours · SURREAL | MPVE: 50.1 -> 44.7 | Improved |
| Increase marker count from 16 to 96 with ground-truth marker positions (ablation) | Virtual marker mesh reconstruction · H3.6M | MPVE: 46.8 -> 9.9 | Improved |
| Increase detected marker count from 64 to 96 (ablation) | Ours · H3.6M | MPVE: 58.0 -> 59.6 | Hurt |
| Use confidence-conditioned updated coefficients instead of a fixed coefficient matrix (ablation) | Ours · H3.6M test | MPVE: 64.7 -> 58.0 | Improved |
| Use confidence-conditioned updated coefficients instead of a fixed coefficient matrix (ablation) | Ours · H3.6M test | MPJPE: 51.6 -> 47.3 | Improved |
| Add confidence loss (ablation) | Ours · H3.6M test | MPVE: 59.2 -> 58.0 | Improved |
| Add pose loss (ablation) | Ours · H3.6M test | MPVE: 58.3 -> 58.0 | Improved |
| Add normal surface loss (ablation) | Ours · H3.6M test | MPVE: 60.6 -> 58.0 | Improved |
| Add edge surface loss (ablation) | Ours · H3.6M test | MPVE: 60.4 -> 58.0 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CLIFF — CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (ECCV 2022) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VMarker-Pro: Probabilistic 3D Human Mesh Estimation From Virtual Markers (TPAMI 2025 · similarity 0.93)
- Deep Virtual Markers for Articulated 3D Shapes (ICCV 2021 · similarity 0.89)
- TexturePose: Supervising Human Mesh Estimation With Texture Consistency (ICCV 2019 · similarity 0.88)
- Recovering 3D Human Mesh From Monocular Images: A Survey (TPAMI 2023 · similarity 0.88)
- End-to-End Recovery of Human Shape and Pose (CVPR 2018 · similarity 0.87)
- MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
