Research map / 3D vision / 3D generation
AffordPose: A Large-Scale Dataset of Hand-Object Interactions with Affordance-Driven Hand Pose
Juntao Jian, Xiuping Liu, Manyi Li, Ruizhen Hu, Jian Liu
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 hand rotation and position (all pose parameters) to the intrinsic joint configuration as input (ablation) | DGCNN affordance classifier · AffordPose affordance classification | mean accuracy (%): 94.40 -> 98.39 | Improved |
| add hand rotation and position to the intrinsic input (ablation) | DGCNN part localization · AffordPose part localization | mean IoU (%): 95.36 -> 96.29 | Improved |
| add rotation and position input for Support affordance (ablation) | DGCNN affordance classifier · AffordPose classification, Support | accuracy (%): 91.58 -> 99.65 | Improved |
| add affordance label (one-hot) as input to GrabNet-style generator | GrabNet · AffordPose hand-object interaction generation | Penetration depth (cm): 0.87 -> 0.89 | No clear effect |
| add affordance label to the generator | GrabNet · AffordPose generation | Solid intersection volume (cm^3): 3.20 -> 4.57 | Hurt |
| add affordance label to the generator | GrabNet · AffordPose generation, objects with several affordances | affordance-distinct hand poses (qualitative) | Improved |
| conditioning on affordance for small-part affordances (pull, twist) | AffordPoseNet · AffordPose generation | Affordance accuracy (%): 0 (pull), 53.13 (twist) | Hurt |
Closest papers by meaning
- OakInk: A Large-Scale Knowledge Repository for Understanding Hand-Object Interaction (CVPR 2022 · similarity 0.92)
- AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis (CVPR 2026 · similarity 0.92)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.91)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.90)
- OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion (CVPR 2024 · similarity 0.89)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 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.
