Research map / 3D vision / Human pose estimation
GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness
HUI YANG, Wei Sun, Jian Liu, Jian Xiao, Tao Xie, Hossein Rahmani, Ajmal Mian, Nicu Sebe, Gim Hee Lee
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 text generation template (ablation) | GenHOI · DexYCB S3 full | MJE: 16.78 -> 13.42 | Improved |
| add multi-level semantic knowledge (ablation) | GenHOI · DexYCB S3 full | ADD-0.5D: 86.32 -> 90.44 | Improved |
| add image masking (ablation) | GenHOI · DexYCB S3 full | MJE: 15.33 -> 13.42 | Improved |
| add text masking (ablation) | GenHOI · DexYCB S3 full | MJE: 14.98 -> 13.42 | Improved |
| add point cloud masking (ablation) | GenHOI · DexYCB S3 full | MJE: 15.21 -> 13.42 | Improved |
| add hand joint prior (ablation) | GenHOI · DexYCB S3 full | ADD-0.5D: 84.01 -> 90.44 | Improved |
| add hand rotation prior (ablation) | GenHOI · DexYCB S3 full | ADD-0.5D: 85.45 -> 90.44 | Improved |
| raise image mask ratio from 50% to 100% (ablation) | GenHOI · DexYCB S3 full | MJE: 13.42 -> 16.75 | Hurt |
| raise text masking ratio from 50% to 75% (ablation) | GenHOI · DexYCB S3 full | ADD-0.5D: 90.44 -> 84.05 | Hurt |
| raise point cloud masking ratio from 30% to 50% (ablation) | GenHOI · DexYCB S3 full | MJE: 13.42 -> 17.35 | Hurt |
| vary image mask patch count from 12 to 4 (ablation) | GenHOI · DexYCB S3 full | MJE: 13.42 -> 14.98 | Hurt |
| use Text->Image->Point fusion order instead of Text->Point->Image (ablation) | GenHOI · DexYCB S3 full | ADD-0.5D: 87.18 -> 90.44 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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
- UniHOPE — UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation (CVPR 2025) · better on 2 of 4 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
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.88)
- UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation (CVPR 2025 · similarity 0.87)
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · similarity 0.87)
- ComPose: When to Trust Hands for Object Pose Tracking (NeurIPS 2026 · similarity 0.86)
- G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis (CVPR 2024 · similarity 0.86)
- HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields (CVPR 2024 · similarity 0.86)
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.
