Research map / 3D vision / Human pose estimation
VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation
Jun Zhou, Chi Xu, Kaifeng Tang, Yuting Ge, Tingrui Guo, Li Cheng
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 force prediction module (ablation) | VPHO baseline · DexYCB Full | object ADD-S (mm): 20.14 -> 16.66 | Improved |
| add force prediction module (ablation) | VPHO baseline · DexYCB Full | hand MJE (mm): 12.54 -> 12.16 | Improved |
| add visual-based aggregation (ablation) | VPHO with force prediction · DexYCB Full | hand MJE (mm): 12.16 -> 10.05 | Improved |
| add physics-based aggregation (ablation) | VPHO with visual aggregation · DexYCB Phy | simulation displacement SD (mm): 20.0 -> 17.3 | Improved |
| add physics-based aggregation (ablation) | VPHO with visual aggregation · DexYCB Full | object OCE (mm): 26.12 -> 23.72 | Improved |
| add physics-based aggregation (ablation) | VPHO with visual aggregation · DexYCB Full | hand MJE (mm): 10.05 -> 10.01 | No clear effect |
| add DexYCB pretraining (ablation) | VPHO · HO3Dv2 Full | object OCE (mm): 29.3 -> 27.1 | Improved |
| add DexYCB pretraining (ablation) | VPHO · HO3Dv2 Full | hand PA-MJE (mm): 8.9 -> 8.5 | Improved |
| VPHO vs HOISDF on HO3Dv2 hand MJE | HOISDF · HO3Dv2 Full | hand MJE (mm): 19.0 -> 19.9 | Hurt |
| joint visual-physical aggregation vs physics-engine training (DeepSimHO) | DeepSimHO · DexYCB Phy | hand MJE (mm): 11.2 -> 8.5 | 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.
- HOISDF — HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields (CVPR 2024) · better on 7 of 8 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
- DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation (NeurIPS 2023 · similarity 0.90)
- ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis (CVPR 2022 · similarity 0.89)
- ComPose: When to Trust Hands for Object Pose Tracking (NeurIPS 2026 · similarity 0.89)
- EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision (ECCV 2026 · similarity 0.89)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.88)
- MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation (NeurIPS 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.
