AI Paper Atlas

Research map / 3D vision / 3D generation

NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model

Zhongqun Zhang, Hengfei Wang, Ziwei Yu, Yihua Cheng, Angela Yao, Hyung Jin Chang

ECCV 2024 · 3D vision › 3D generation · approach: Hand-object interaction generation · 10 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
add natural language contact description guidance (ablation)NL2Contact · ContactDescribeMPJPE (mm): 24.3 -> 21.7Improved
use more specific low-level text instead of high-level text (ablation)NL2Contact · ContactDescribeMPJPE (mm): 23.9 -> 21.7Improved
add cascaded text-to-hand attention fusion (ablation)NL2Contact · ContactDescribeMPJPE (mm): 23.5 -> 21.7Improved
add text-to-hand-object fusion into point features (ablation)NL2Contact · ContactDescribeMPJPE (mm): 22.9 -> 21.7Improved
use staged diffusion (hand pose first, then contact) rather than a single stage (ablation)NL2Contact · ContactDescribeMPJPE (mm): 27.3 -> 21.7Improved
use diffusion instead of VAE generators (ablation)NL2Contact · ContactDescribeMPJPE (mm): 21.9 -> 21.7Improved
use NL2Contact contact maps vs ContactOpt for grasp optimizationgrasp pose optimization · ContactDescribeintersection volume: 12.8 -> 7.1Improved
use NL2Contact vs S2Contact on Described HO3Dgrasp pose optimization · Described HO3Dintersection volume (mm^3): 3.52 vs 4.39Hurt
use NL2Contact vs S2Contact on Described HO3Dgrasp pose optimization · Described HO3DMPJPE (mm): 8.7 -> 8.4Improved
use NL2Contact vs ContactGen for grasp generationhuman grasp generation · unseen HO3D objectsdiversity: 5.04 -> 5.91Improved

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