Research map / 3D vision / Human pose estimation
Semi-Supervised 3D Hand-Object Poses Estimation With Interactions in Time
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 object-query contextual reasoning to the object features (ablation) | Joint hand-object pose model · HO-3D | Average object ADD-0.1D: 62.2 -> 67.7 | Helped |
| Use hand features as the CR query instead of object features (ablation) | Joint hand-object pose model · HO-3D | Hand mesh error (mm): 9.7 -> 9.8 | Hurt |
| Add semi-supervised training with filtered video pseudo-labels | Model with contextual reasoning · HO-3D | Average object ADD-0.1D: 67.7 -> 76.1 | Helped |
| Add semi-supervised training with filtered video pseudo-labels | Hand-object pose model · HO-3D | Hand mesh error (mm): 9.7 -> 9.5 | Helped |
| Remove spatial pseudo-label filtering (ablation) | Semi-supervised hand pose model · HO-3D | Hand mesh error (mm): 9.5 -> 9.9 | Hurt |
| Remove temporal pseudo-label filtering (ablation) | Semi-supervised hand pose model · HO-3D | Hand mesh error (mm): 9.5 -> 9.8 | Hurt |
| Add video pseudo-label training | Hand pose model · FPHA | Mesh AUC: 74.6 -> 76.0 | Helped |
| Add video pseudo-label training | Hand pose model · Freihand | Mesh AUC: 68.2 -> 69.6 | Helped |
| Use more pseudo hand labels (ablation) | Semi-supervised joint hand-object model · HO-3D | Object ADD-0.1D | Helped |
Closest papers by meaning
- Efficiently Creating 3D Training Data for Fine Hand Pose Estimation (CVPR 2016 · similarity 0.91)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.90)
- SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (ICLR 2025 · similarity 0.89)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields (CVPR 2024 · similarity 0.88)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · 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.