AI Paper Atlas

Research map / 3D vision / 3D generation

CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild

Balamurugan Thambiraja, Omid Taheri, Radek Danecek, Giorgio Becherini, Gerard Pons-Moll, Justus Thies

ICLR 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation

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 geometric refinement (Gumbel-Softmax reconstruction loss) stage (ablation)CLUTCH · 3D-HIW test, text-to-motionKID: 0.297 -> 0.216Improved
add geometric refinement stage (ablation)CLUTCH · 3D-HIW test, text-to-motionRP3: 0.690 -> 0.721Improved
add instruction fine-tuning after pre-training (ablation)CLUTCH · 3D-HIW test, text-to-motionRP3: 0.53 -> 0.69Improved
use Gumbel-Softmax geometric refinement instead of EgoLM soft-blending regression (ablation)CLUTCH · 3D-HIW test, text-to-motionKID: 0.263 -> 0.216Improved
geometric refinement on motion-to-text captioning (ablation)CLUTCH · 3D-HIW test, motion-to-textRP3: 0.568 -> 0.571No clear effect
use SHIFT decomposed tokenizer (trajectory/pose and left/right) instead of standard VQ-VAE (ablation)CLUTCH tokenizer · 3D-HIW motion reconstructionMPJPE: 93.258 -> 45.944Improved
left/right hand separation only (PD VQ-VAE) without trajectory/pose split (ablation)VQ-VAE tokenizer · 3D-HIW motion reconstructionMPJPE: 93.258 -> 95.266No clear effect
enlarge VQ-VAE codebook from 4K to 8K for standard VQ-VAE (ablation)Std VQ-VAE · 3D-HIW motion reconstructionMPJPE: 93.258 -> 92.150No clear effect
two-stage parallel chain-of-thought annotation instead of single naive prompt (ablation)VILA annotation · 3D-HIW annotation qualityGPT-Score: 5.5 -> 6.9Improved
add closed-vocabulary stage 2 after stage 1 (ablation)VILA annotation · 3D-HIW annotation qualityGPT-Score: 6.4 -> 6.9Improved
use combined high-level and fine-grained text annotations instead of either alone (ablation)CLUTCH · 3D-HIW test, text-to-motionRP3: 0.551 -> 0.721Improved
increase training data from 7K to 30K sequences (ablation)CLUTCH · 3D-HIW test, text-to-motionRP3: 0.513 -> 0.721Improved

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