AI Paper Atlas

Research map / 3D vision / 3D generation

ContactGen: Generative Contact Modeling for Grasp Generation

Shaowei Liu, Yang Zhou, Jimei Yang, Saurabh Gupta, Shenlong Wang

ICCV 2023 · 3D vision › 3D generation · approach: Hand-object interaction generation · 46 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
represent contact with part and direction maps in addition to contact map (ContactGen vs TOCH)contact-to-grasp recovery · GRAB (recovery from GT contact)EPE (cm): 3.44 -> 1.49Improved
use sequential (hierarchical) CVAE instead of joint modeling of the three maps (ablation)ContactGen CVAE · GRAB grasp synthesisSimulation displacement: 3.29 -> 2.16Improved
use sequential CVAE instead of separate modeling of the three maps (ablation)ContactGen CVAE · GRAB grasp synthesisContact ratio: 0.89 -> 0.96Improved
sequential decomposition versus separate modeling on diversity (ablation)ContactGen CVAE · GRAB grasp synthesisCluster size: 4.83 -> 4.11Hurt
add part map and direction map to contact map (SDF hand) (ablation)ContactGen contact solver · GRAB grasp synthesisPenetration volume: 20.13 -> 2.72Improved
add direction map on top of contact and part maps (SDF hand) (ablation)ContactGen contact solver · GRAB grasp synthesisSimulation displacement: 6.81 -> 2.16Improved
add part and direction maps (MANO hand) (ablation)contact solver with MANO · GRAB grasp synthesisPenetration volume: 7.41 -> 2.36Improved
use piecewise SDF hand instead of MANO with full representation (ablation)contact solver · GRAB grasp synthesisSimulation displacement: 2.85 -> 2.16Improved
use ContactGen instead of HALO on HO3Dgrasp synthesis · HO3D grasp synthesis (out-of-domain)Penetration volume: 25.84 -> 9.96Improved
use ContactGen instead of GrabNet on GRABgrasp synthesis · GRAB grasp synthesisSimulation displacement: 1.72 -> 2.16Hurt
use ContactGen instead of HALO in human study (GRAB naturalness)grasp synthesis · GRAB human studyNatural score: 2.59 -> 3.21Improved

Later papers that compared with this method

6 later accepted papers report ContactGen as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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