Saved in:
Bibliographic Details
Main Authors: Xiao, Lijingze, Du, Jinhong, Diao, Supeng, Ren, Yu, Cong, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29254
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911595132616704
author Xiao, Lijingze
Du, Jinhong
Diao, Supeng
Ren, Yu
Cong, Yang
author_facet Xiao, Lijingze
Du, Jinhong
Diao, Supeng
Ren, Yu
Cong, Yang
contents Robotic grasping from single-view observations remains a critical challenge in manipulation. However, existing methods still struggle to generate reliable grasp candidates and stably evaluate grasp feasibility under incomplete geometric information. To address these limitations, we present SuperGrasp, a new two-stage framework for single-view parallel-jaw grasping. In the first stage, we introduce a Similarity Matching Module that efficiently retrieves valid and diverse grasp candidates by matching the input single-view point cloud with a precomputed primitive dataset based on superquadric coefficients. In the second stage, we propose E-RNet, an end-to-end network that expands the grasp-aware region and takes the initial grasp closure region as a local anchor region, capturing the contextual relationship between the local region and its surrounding spatial neighborhood, thereby enabling more accurate and reliable grasp evaluation and introducing small-range local refinement to improve grasp adaptability. To enhance generalization, we construct a primitive dataset containing 1.2k standard geometric primitives for similarity matching and collect a point cloud dataset of 100k samples from 124 objects, annotated with stable grasp labels for network training. Extensive experiments in both simulation and real-world environments demonstrate that our method achieves stable grasping performance and good generalization across novel objects and clutter scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29254
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement
Xiao, Lijingze
Du, Jinhong
Diao, Supeng
Ren, Yu
Cong, Yang
Robotics
Robotic grasping from single-view observations remains a critical challenge in manipulation. However, existing methods still struggle to generate reliable grasp candidates and stably evaluate grasp feasibility under incomplete geometric information. To address these limitations, we present SuperGrasp, a new two-stage framework for single-view parallel-jaw grasping. In the first stage, we introduce a Similarity Matching Module that efficiently retrieves valid and diverse grasp candidates by matching the input single-view point cloud with a precomputed primitive dataset based on superquadric coefficients. In the second stage, we propose E-RNet, an end-to-end network that expands the grasp-aware region and takes the initial grasp closure region as a local anchor region, capturing the contextual relationship between the local region and its surrounding spatial neighborhood, thereby enabling more accurate and reliable grasp evaluation and introducing small-range local refinement to improve grasp adaptability. To enhance generalization, we construct a primitive dataset containing 1.2k standard geometric primitives for similarity matching and collect a point cloud dataset of 100k samples from 124 objects, annotated with stable grasp labels for network training. Extensive experiments in both simulation and real-world environments demonstrate that our method achieves stable grasping performance and good generalization across novel objects and clutter scenes.
title SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement
topic Robotics
url https://arxiv.org/abs/2603.29254