Research map / 3D vision / Depth and stereo
JUMP-Hand: Learning Joint-wise Uncertainty to Gate Mixture of View Experts for Multi-View 3D Hand Reconstruction
Haohong Kuang, Yang Xiao, Changlong Jiang, Jinghong Zheng, Hang Xu, Ran Wang, Zhiguo Cao, Joey Tianyi Zhou
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 uncertainty-based gating instead of average gating (ablation) | JUMP-Hand · HO3D-MV | MPJPE (mm): 16.31 -> 13.10 | Improved |
| use uncertainty-based gating instead of learnable router gating (ablation) | JUMP-Hand · HO3D-MV | MPJPE (mm): 15.54 -> 13.10 | Improved |
| add refinement stage after UG-DLT (ablation) | JUMP-Hand · HO3D-MV | MPJPE (mm): 16.61 -> 13.10 | Improved |
| add uncertainty-guided coarse stage (ablation) | JUMP-Hand · HO3D-MV | MPJPE (mm): 21.55 -> 13.10 | Improved |
| use soft gating over all views instead of hard top-2 (ablation) | JUMP-Hand · HO3D-MV | MPJPE (mm): 18.16 -> 13.10 | Improved |
| use soft gating instead of hard top-3 (ablation) | JUMP-Hand · HO3D-MV | MPJPE (mm): 15.47 -> 13.10 | Improved |
| use soft gating instead of hard top-4 (ablation) | JUMP-Hand · DexYCB-MV | MPJPE (mm): 5.70 -> 5.31 | Improved |
| use soft gating instead of hard top-3 (ablation) | JUMP-Hand · OakInk-MV | MPJPE (mm): 5.88 -> 5.72 | Improved |
| replace POEM fusion with JUMP-Hand | POEM · HO3D-MV | MPVPE (mm): 17.20 -> 13.39 | Improved |
| replace POEM fusion with JUMP-Hand | POEM · HO3D challenging subset | MPVPE (mm): 35.52 -> 24.91 | Improved |
| replace POEM fusion with JUMP-Hand | POEM · OakInk-MV | MPVPE (mm): 6.20 -> 5.94 | 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.
- MLPHand — MLPHand: Real Time Multi-View 3D Hand Reconstruction via MLP Modeling (ECCV 2024) · better on 3 of 3 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
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.88)
- SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation (AAAI 2024 · similarity 0.88)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (AAAI 2024 · similarity 0.87)
- HandOS: 3D Hand Reconstruction in One Stage (CVPR 2025 · similarity 0.87)
- Monocular 3D Hand Mesh Recovery via Dual Noise Estimation (AAAI 2024 · similarity 0.87)
- Pose-Guided Temporal Enhancement for Robust Low-Resolution Hand Reconstruction (CVPR 2025 · 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.
