MG-Grasp: Metric-Scale Geometric 6-DoF Grasping Framework with Sparse RGB Observations

TL;DR

MG-Grasp introduces a depth-free 6-DoF grasping framework that reconstructs dense 3D point clouds from sparse RGB images, enabling reliable robotic grasping without depth sensors and achieving state-of-the-art results.

Contribution

The paper presents a novel RGB-only 6-DoF grasping method that reconstructs metric-scale 3D point clouds from sparse images for improved grasp reliability.

Findings

Achieves state-of-the-art grasping performance on GraspNet-1Billion.

Reconstructs accurate metric-scale 3D models from sparse RGB images.

Operates effectively without depth sensors.

Abstract

Single-view RGB-D grasp detection remains a common choice in 6-DoF robotic grasping systems, which typically requires a depth sensor. While RGB-only 6-DoF grasp methods has been studied recently, their inaccurate geometric representation is not directly suitable for physically reliable robotic manipulation, thereby hindering reliable grasp generation. To address these limitations, we propose MG-Grasp, a novel depth-free 6-DoF grasping framework that achieves high-quality object grasping. Leveraging two-view 3D foundation model with camera intrinsic/extrinsic, our method reconstructs metric-scale and multi-view consistent dense point clouds from sparse RGB images and generates stable 6-DoF grasp. Experiments on GraspNet-1Billion dataset and real world demonstrate that MG-Grasp achieves state-of-the-art (SOTA) grasp performance among RGB-based 6-DoF grasping methods.