Research map / 3D vision / 3D generation
Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves
Xinyu Zhang, Ziyi Kou, Chuan Qin, Mia Huang, Ergys Ristani, Ankit Kumar, Lele Chen, Kun He, Abdeslam Boularias, Li Guan
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 |
|---|---|---|---|
| anchor Gaussians on the mesh surface instead of 2DGS (ablation) | Glove2Hand hand model · HandSense glove-to-hand translation | FID: 91.1 -> 60.3 | Improved |
| add relightable Gaussians with pose-conditioned lighting (ablation) | Glove2Hand hand model · HandSense glove-to-hand translation | FID: 60.3 -> 56.7 | Improved |
| add diffusion hand restorer (ablation) | Glove2Hand · HandSense glove-to-hand translation | FID: 56.7 -> 32.3 | Improved |
| add glove removal inpainting (ablation) | Glove2Hand · HandSense glove-to-hand translation | FID: 32.3 -> 31.2 | Mixed |
| add object mask (ablation) | Glove2Hand · HandSense glove-to-hand translation | FID: 31.2 -> 30.1 | Improved |
| Glove2Hand instead of HandRefiner | video translation · HandSense glove-to-hand translation | FID: 35.5 -> 30.1 | Improved |
| train contact estimator on G2H videos instead of glove videos | contact estimator · HandSense contact estimation (real test videos) | Contact IoU: 71.5 -> 75.6 | Improved |
| add G2H data to real hand data | contact estimator · HandSense contact estimation (real test videos) | Contact IoU: 85.3 -> 88.2 | Improved |
| finetune UmeTrack on G2H videos | UmeTrack · HandSense hand tracking (occlusion subset) | MKPE: 19.2 -> 16.6 | Improved |
| finetune UmeTrack on raw glove videos | UmeTrack · HandSense hand tracking (occlusion subset) | MKPE: 19.2 -> 27.2 | Hurt |
Closest papers by meaning
- HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction (NeurIPS 2025 · similarity 0.89)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios (NeurIPS 2025 · similarity 0.89)
- Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling (AAAI 2024 · similarity 0.89)
- MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation (NeurIPS 2025 · similarity 0.89)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.89)
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.
