Research map / 3D vision / Human pose estimation
A Dataset of Relighted 3D Interacting Hands
Gyeongsik Moon, Shunsuke Saito, Weipeng Xu, Rohan Joshi, Julia Buffalini, Harley Bellan, Nicholas Matthew Rosen, Jesse Richardson, Mallorie Mize, Philippe De Bree, Tomas Simon, Bo Peng and 3 more
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 capture-stage data (ablation) | InterWild training · InterHand2.6M test | RRVE: 19.74 -> 19.14 | Improved |
| add capture-stage data (ablation) | InterWild training · HIC test | RRVE: 23.59 -> 23.09 | Improved |
| add capture-stage data (ablation) | InterWild training · Re:InterHand test | RRVE: 37.59 -> 34.23 | Improved |
| add composite images (ablation) | InterWild training · HIC test | RRVE: 23.59 -> 24.37 | Hurt |
| add composite images (ablation) | InterWild training · Re:InterHand test | RRVE: 37.59 -> 31.30 | Improved |
| add AdaIn harmonization to composite (ablation) | InterWild training · HIC test | RRVE: 24.37 -> 24.83 | Hurt |
| add AdaIn harmonization to composite (ablation) | InterWild training · Re:InterHand test | RRVE: 31.30 -> 27.96 | Improved |
| use relight stage instead of composite (ablation) | InterWild training · HIC test | RRVE: 24.37 -> 21.36 | Improved |
| use relight stage instead of capture stage only (ablation) | InterWild training · InterHand2.6M test | RRVE: 19.14 -> 19.40 | Mixed |
| add relight stage data vs baseline (ablation) | InterWild training · InterHand2.6M test | RRVE: 19.74 -> 19.40 | Improved |
| add relight stage data vs baseline (ablation) | InterWild training · Re:InterHand test | RRVE: 37.59 -> 20.07 | Improved |
| train InterWild additionally on Re:InterHand | InterWild · HIC test | RRVE: 23.59 -> 21.36 | Improved |
Closest papers by meaning
- InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image (ECCV 2020 · similarity 0.91)
- Reconstructing Hand-Object Interactions in the Wild (ICCV 2021 · similarity 0.91)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.89)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.89)
- How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions (CVPR 2025 · similarity 0.89)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
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.
