Research map / 3D vision / Human pose estimation
DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling
Gyeongsik Moon, Takaaki Shiratori, Kyoung Mu Lee
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 DeepHandMesh decoder instead of pre-trained MANO decoder | DeepHandMesh · Own hand dataset, unseen poses | P_err (mm): 13.81 -> 9.86 | Improved |
| use DeepHandMesh decoder instead of pre-trained MANO decoder | DeepHandMesh · Own hand dataset, unseen poses | M_err (mm): 8.93 -> 6.55 | Improved |
| add identity-dependent skeleton corrective (ablation) | DeepHandMesh · Own hand dataset | P_err (mm): 4.82 -> 2.38 | Improved |
| add pose loss L_pose (ablation) | DeepHandMesh · Own hand dataset (qualitative) | mesh quality | Improved |
| add penetration avoidance loss L_penet (ablation) | DeepHandMesh · Own hand dataset (qualitative) | mesh quality | Improved |
| add identity-dependent correctives (ablation) | DeepHandMesh · Own hand dataset (qualitative) | personalization | Improved |
| add pose-dependent per-vertex corrective (ablation) | DeepHandMesh · Own hand dataset (qualitative) | detail recovery | Improved |
| add texture loss L_tex during fine-tuning (ablation) | DeepHandMesh texture · Own hand dataset | pixel std in UV space | Improved |
| train Kulon et al. model without per-vertex mesh supervision | Kulon et al. · Own hand dataset (qualitative) | mesh quality | Hurt |
Closest papers by meaning
- Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild (CVPR 2020 · similarity 0.92)
- TokenHand: Discrete Token Representation for Efficient Hand Mesh Reconstruction (CVPR 2026 · similarity 0.90)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.89)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.88)
- A Simple Baseline for Efficient Hand Mesh Reconstruction (CVPR 2024 · similarity 0.88)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.87)
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.
