Dexterous Grasp Transformer

TL;DR

This paper introduces DGTR, a transformer-based framework for dexterous grasp generation that predicts diverse, high-quality grasp poses efficiently, overcoming optimization challenges with novel training and testing strategies.

Contribution

The paper presents a new set prediction approach for dexterous grasping, along with progressive training and testing strategies to improve performance and diversity.

Findings

DGTR achieves high-quality, diverse grasp predictions on DexGraspNet.

It outperforms previous methods in grasp diversity metrics.

The proposed strategies enhance training stability and test-time adaptation.

Abstract

In this work, we propose a novel discriminative framework for dexterous grasp generation, named Dexterous Grasp TRansformer (DGTR), capable of predicting a diverse set of feasible grasp poses by processing the object point cloud with only one forward pass. We formulate dexterous grasp generation as a set prediction task and design a transformer-based grasping model for it. However, we identify that this set prediction paradigm encounters several optimization challenges in the field of dexterous grasping and results in restricted performance. To address these issues, we propose progressive strategies for both the training and testing phases. First, the dynamic-static matching training (DSMT) strategy is presented to enhance the optimization stability during the training phase. Second, we introduce the adversarial-balanced test-time adaptation (AB-TTA) with a pair of adversarial losses to improve grasping quality during the testing phase. Experimental results on the DexGraspNet dataset demonstrate the capability of DGTR to predict dexterous grasp poses with both high quality and diversity. Notably, while keeping high quality, the diversity of grasp poses predicted by DGTR significantly outperforms previous works in multiple metrics without any data pre-processing. Codes are available at https://github.com/iSEE-Laboratory/DGTR .