AI Paper Atlas

Research map / 3D vision / 3D generation

Scalable Cross-embodiment Dexterous Grasping via Morphology-Prior Diffusion

Sihang Li, Zheming Zhou, Marcelino Almeida, Omid Alizadeh, Luca Carlone, Min Sun, Chen Feng, Cheng-Hao Kuo

ECCV 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 0 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
scale from 3 to 7 handsSOMO · Grasp synthesisavg. success: 92.37 -> 78.93 (-13.4 pp), baselines 87.53 -> 64.45 and 93.90 -> 63.72Mixed
add more data (extended dataset with XHand)SOMO · 7 handsavg. success: 78.93 -> 81.02Improved
add more data (extended dataset)D(R,O) and T(R,O) · 7 handsavg. success: 64.45 -> 63.91 and 63.72 -> 65.87No clear effect
use classifier-free morphology prior for held-out handSOMO vs D(R,O) · annotation-free Allegrosuccess rate: 93.30% vs. 43.20%Improved
use classifier-free morphology prior for held-out handSOMO vs D(R,O) · annotation-free LeapHandsuccess rate: 32.40% vs. 2.80%Improved
add variable-length tokens instead of fixed-topology graph (ablation)SOMO · 4 supervised handsavg. success: +0.96 ppImproved
replace BPS link encoding with VAE (ablation)SOMO · 4 supervised handsavg. success: +2.25 pp (79.38 -> 81.63)Improved
replace VQVAE object encoding with VAE (ablation)SOMO · 4 supervised handsavg. success: +1.12 pp (81.63 -> 82.75)Improved
guidance scale 1.25 instead of 1.0 for annotation-free hand (ablation)SOMO · Barrett (annotation-free)success rate: 81.4 -> 83.1Improved
guidance scale 1.0 instead of 1.25 for supervised hands (ablation)SOMO · Allegro/Shadow avg.success rate: 93.6 -> 94.2Improved
raise guidance scale to 2.0 (ablation)SOMO · Barrett and avg. of supervised handssuccess rate: 83.1 -> 79.9 (Barrett), 94.2 -> 89.9 (avg.)Hurt
use SOMO under 50% partial point cloudsSOMO · 6 handsavg. success: 70.70 vs 55.85 and 55.43Improved

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