Research map / 3D vision / 3D generation
GRAB: A Dataset of Whole-Body Human Grasping of Objects
Omid Taheri, Nima Ghorbani, Michael J. Black, Dimitrios Tzionas
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 |
|---|---|---|---|
| use GrabNet generated grasps instead of ground-truth grasps (frying pan) | GrabNet · GRAB test object: frying pan | AMT grasp quality (1-5 Likert): 4.49 -> 3.19 | Hurt |
| use GrabNet generated grasps instead of ground-truth grasps (average over 6 objects) | GrabNet · GRAB 6 test objects | AMT grasp quality (1-5 Likert): 4.38 -> 4.12 | Hurt |
| use GrabNet generated grasps instead of ground-truth grasps (camera) | GrabNet · GRAB test object: camera | AMT grasp quality (1-5 Likert): 4.34 -> 4.40 | No clear effect |
| use GrabNet generated grasps instead of ground-truth grasps (toothpaste) | GrabNet · GRAB test object: toothpaste | AMT grasp quality (1-5 Likert): 4.42 -> 4.56 | No clear effect |
| apply RefineNet after CoarseNet, test-set reconstruction error of each module | GrabNet · GRAB test set | reconstruction vertex-to-vertex error (mm): 18.4 -> 4.4 | Mixed |
| switch intent from use to pass in captured grasps | GRAB contact analysis · GRAB contact heatmaps | contact pattern | Mixed |
Closest papers by meaning
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.90)
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 2025 · similarity 0.89)
- MANUS: Markerless Grasp Capture using Articulated 3D Gaussians (CVPR 2024 · similarity 0.89)
- LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion. (CVPR 2025 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.89)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 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.
