Research map / 3D vision / Human pose estimation
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
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 ArtiBoost synthetic training data | Clas and Reg on HO3D · HO3D | MPJPE: 3.53 -> 3.17; 3.06 -> 2.64 | Helped |
| Add ArtiBoost synthetic training data | Clas and Reg on HO3D · HO3D | MPCPE: 7.38 -> 5.87; 7.24 -> 5.16 | Helped |
| Add ArtiBoost synthetic training data | symmetry-aware Clas · HO3D | MPJPE: 3.10 -> 2.53 | Helped |
| Add ArtiBoost synthetic training data | symmetry-aware Clas · DexYCB S0 | MPJPE: 13.00 -> 12.80 | Helped |
| Replace conventional YCBAfford grasps with CCV-space grasps (ablation) | Clas trained on HO3D · HO3D | MPJPE: 3.01 -> 2.71 | Helped |
| Replace conventional YCBAfford grasps with CCV-space grasps (ablation) | Clas trained on HO3D · HO3D | MPCPE: 6.89 -> 5.49 | Helped |
| Add full ArtiBoost, including online reweighting, after CCV-space synthesis (ablation) | Clas trained on HO3D · HO3D | MPJPE: 2.71 -> 2.64 | Helped |
| Add full ArtiBoost, including online reweighting, after CCV-space synthesis (ablation) | Clas trained on HO3D · HO3D | MPCPE: 5.49 -> 5.16 | Helped |
| Remove ordinal relation loss (ablation) | Clas on FHAB · FHAB action test | MPJPE: 8.60 -> 8.71 | Hurt |
| Remove ordinal relation loss (ablation) | Clas on FHAB · FHAB action test | MPCPE: 19.45 -> 18.64 | Mixed |
| Use online sample reweighting instead of fixed uniform sampling weights (ablation) | symmetry-aware Clas on DexYCB · DexYCB | convergence and final score | Helped |
| Add ArtiBoost synthetic data with only 10% of the real training set | Reg and Clas · HO3D | MPJPE: 3.81 -> 3.29; 3.63 -> 3.05 | Mixed |
Closest papers by meaning
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.90)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.90)
- HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields (CVPR 2024 · similarity 0.89)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.89)
- SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (ICLR 2025 · similarity 0.89)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (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.