AI Paper Atlas

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

ECCV 2020 · 3D vision › 3D generation · approach: Hand-object interaction generation · 372 citations (OpenAlex)

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 changedWhereMeasuredEffect
use GrabNet generated grasps instead of ground-truth grasps (frying pan)GrabNet · GRAB test object: frying panAMT grasp quality (1-5 Likert): 4.49 -> 3.19Hurt
use GrabNet generated grasps instead of ground-truth grasps (average over 6 objects)GrabNet · GRAB 6 test objectsAMT grasp quality (1-5 Likert): 4.38 -> 4.12Hurt
use GrabNet generated grasps instead of ground-truth grasps (camera)GrabNet · GRAB test object: cameraAMT grasp quality (1-5 Likert): 4.34 -> 4.40No clear effect
use GrabNet generated grasps instead of ground-truth grasps (toothpaste)GrabNet · GRAB test object: toothpasteAMT grasp quality (1-5 Likert): 4.42 -> 4.56No clear effect
apply RefineNet after CoarseNet, test-set reconstruction error of each moduleGrabNet · GRAB test setreconstruction vertex-to-vertex error (mm): 18.4 -> 4.4Mixed
switch intent from use to pass in captured graspsGRAB contact analysis · GRAB contact heatmapscontact patternMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy