Research map / Detection and segmentation / Open-set and few-shot detection
OakInk: A Large-Scale Knowledge Repository for Understanding Hand-Object Interaction
Lixin Yang, Kailin Li, Xinyu Zhan, Fei Wu, Anran Xu, Liu Liu, Cewu Lu
Check 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 |
|---|---|---|---|
| Train the pose estimator on OakInk-Image instead of HO3D | Image-based 3D pose estimation model · DexYCB test set | MPJPE (mm): 55.38 -> 44.81 | Improved |
| Mix OakInk-Image training data with HO3D | Image-based 3D pose estimation model · DexYCB test set | MPJPE (mm): 55.38 -> 39.70 | Improved |
| Condition GrabNet on an intent embedding | IntGen · OakInk-Shape, mug | Perceptual score: 3.66 -> 3.86 | Improved |
| Condition GrabNet on an intent embedding | IntGen · OakInk-Shape, trigger sprayer | Perceptual score: 3.66 -> 3.93 | Improved |
| Condition GrabNet on an intent embedding | IntGen · OakInk-Shape, camera | Penetration depth (cm): 0.67 -> 1.54 | Hurt |
| Condition GrabNet on an intent embedding | IntGen · OakInk-Shape, camera | Perceptual score: 3.66 -> 3.94 | Improved |
| Condition GrabNet on an intent embedding | IntGen · OakInk-Shape, lotion bottle | Penetration depth (cm): 0.67 -> 1.57 | Hurt |
| Condition GrabNet on an intent embedding | IntGen · OakInk-Shape, lotion bottle | Perceptual score: 3.66 -> 3.98 | Improved |
| Condition GrabNet on the giver's hand pose for receiving | HoverGen · OakInk-Shape handover | Perceptual score: 3.66 -> 4.03 | Improved |
| Condition GrabNet on the giver's hand pose for receiving | HoverGen · OakInk-Shape handover | Simulation displacement mean (cm): 1.21 -> 1.30 | Hurt |
Closest papers by meaning
- AffordPose: A Large-Scale Dataset of Hand-Object Interactions with Affordance-Driven Hand Pose (ICCV 2023 · similarity 0.92)
- OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion (CVPR 2024 · similarity 0.90)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.89)
- How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions (CVPR 2025 · similarity 0.88)
- Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction (CVPR 2024 · similarity 0.87)
- ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions (CVPR 2025 · similarity 0.87)
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.
