DexDiffuser: Generating Dexterous Grasps with Diffusion Models
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:BFQJDP7Qrecord.jsonopen to challenge →
read the original abstract
We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and the dexterous grasp evaluator DexEvaluator. DexSampler generates high-quality grasps conditioned on object point clouds by iterative denoising of randomly sampled grasps. We also introduce two grasp refinement strategies: Evaluator-Guided Diffusion (EGD) and Evaluator-based Sampling Refinement (ESR). The experiment results demonstrate that DexDiffuser consistently outperforms the state-of-the-art multi-finger grasp generation method FFHNet with an, on average, 9.12% and 19.44% higher grasp success rate in simulation and real robot experiments, respectively. Supplementary materials are available at https://yulihn.github.io/DexDiffuser_page/
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning
EAGG uses embodiment-specific graphs and iterative geometry injection in a shared generator to achieve 56.17% average success across six end-effectors on MultiGripperGrasp, within 1.10 pp of specialized models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.