Research map / 3D vision / Depth and stereo
Multi-View Hand Reconstruction With a Point-Embedded Transformer
Lixin Yang, Licheng Zhong, Pengxiang Zhu, Xinyu Zhan, Junxiao Kong, Jian Xu, Cewu Lu
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 |
|---|---|---|---|
| add two-stage design (root estimation then root-relative mesh) (ablation) | POEM · DexYCB-Mv | MPVPE: 9.42 -> 6.13 | Improved |
| add point-embedded transformer decoder instead of PE-MeshTR decoder (ablation) | POEM · DexYCB-Mv | MPVPE: 7.63 -> 6.13 | Improved |
| add point-embedded transformer decoder instead of PE-MeshTR decoder (ablation) | POEM · HO3D-Mv | MPVPE: 19.26 -> 17.20 | Improved |
| add projective aggregation of basis points (ablation) | POEM · DexYCB-Mv | MPVPE: 6.57 -> 6.13 | Improved |
| add projective aggregation of basis points (ablation) | POEM · OakInk-Mv | MPVPE: 6.42 -> 6.20 | Improved |
| add projective aggregation of basis points (ablation) | POEM · HO3D-Mv | MPVPE: 18.83 -> 17.20 | Improved |
| use vertex-level embedding (V-emb) instead of G-emb queries (ablation) | POEM · OakInk-Mv | MPVPE: 6.25 -> 6.20 | Improved |
| use V-emb instead of G&V-emb queries (ablation) | POEM · OakInk-Mv | MPVPE: 6.23 -> 6.20 | Improved |
| POEM vs MvP baseline | POEM · HO3D-Mv | MPVPE: 20.95 -> 17.20 | Improved |
| POEM vs iterative optimization | POEM · DexYCB-Mv | MPVPE: 7.33 -> 6.13 | Improved |
| shuffle camera order at test time | POEM · DexYCB-Mv | MPVPE: 6.13 -> 20.40 | Hurt |
| train on HO3D and test on OakInk-Mv | POEM · OakInk-Mv | MPVPE: 6.20 -> 29.9 | Hurt |
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.
- Hamba — Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba (NeurIPS 2024) · better on 1 of 1 shared result
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
- Monocular 3D Hand Mesh Recovery via Dual Noise Estimation (AAAI 2024 · similarity 0.87)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.86)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.86)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.86)
- Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera (CVPR 2025 · similarity 0.86)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.85)
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.
