mlsanityData to 14 Oct 2026

3DSGrasp: 3D Shape-Completion for Robotic Grasp

arXiv 2301.00866 ↗First posted 2 Jan 2023cs.RO cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. However, in practice, PCDs are often incomplete when objects are viewed from few and sparse viewpoints before the grasping action, leading to the generation of wrong or inaccurate grasp poses. We propose a novel grasping strategy, named 3DSGrasp, that predicts the missing geometry from the partial PCD to produce reliable grasp poses. Our proposed PCD completion network is a Transformer-based encoder-decoder network with an Offset-Attention layer. Our network is inherently invariant to the object pose and point's permutation, which generates PCDs that are geometrically consistent and completed properly. Experiments on a wide range of partial PCD show that 3DSGrasp outperforms the best state-of-the-art method on PCD completion tasks and largely improves the grasping success rate in real-world scenarios. The code and dataset will be made available upon acceptance.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 2 Jan 2023.

Builds on

26 of 42 references.

References · 26

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2020PCT: Point cloud transformercited by 732
  6. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  7. 2018PCN: Point Completion Networkcited by 384
  8. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  9. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  10. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 218
  11. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  12. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
14 more
  1. 2013Deep Learning for Detecting Robotic Graspscited by 116
  2. 2017Grasp Pose Detection in Point Cloudscited by 111
  3. 2021CAT: Cross Attention in Vision Transformercited by 92
  4. 2014Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Studycited by 89
  5. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  6. 2016Shape Completion Enabled Robotic Graspingcited by 79
  7. 2014Real-Time Grasp Detection Using Convolutional Neural Networkscited by 76
  8. 2019Learning Continuous 3D Reconstructions for Geometrically Aware Graspingcited by 29
  9. 2019Robust Grasp Planning Over Uncertain Shape Completionscited by 16
  10. 2021Online Object Model Reconstruction and Reuse for Lifelong Improvement of Robot Manipulationcited by 10
  11. 2018High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimizationcited by 9
  12. 2020Robotic Grasping through Combined Image-Based Grasp Proposal and 3D Reconstructioncited by 9
  13. 2021Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Resultscited by 9
  14. 2021TransSC: Transformer-based Shape Completion for Grasp Evaluationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 8.

13 papers.

Sort:

By area:

  1. 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Graspingcited by 13
  2. 2023Progressive Text-to-3D Generation for Automatic 3D Prototypingcited by 9
  3. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  4. 2025LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoningcited by 8
  5. 2023High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformerscited by 6
  6. 2023Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Renderingcited by 5
  7. 2025MaskPlanner: Learning-Based Object-Centric Motion Generation from 3D Point Cloudscited by 3
  8. 2025SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splattingcited by 3
  9. 2024You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objectscited by 2
  10. 2025GRASPLAT: Enabling dexterous grasping through novel view synthesiscited by 2
  11. 2025PCF-Grasp: Converting Point Completion to Geometry Feature to Enhance 6-DoF Graspcited by 1
  12. 2025Grasp the Graph (GtG) 2.0: Ensemble of Graph Neural Networks for High-Precision Grasp Pose Detection in Cluttercited by 1
1 more
  1. 2025A Multi-Level Similarity Approach for Single-View Object Grasping: Matching, Planning, and Fine-Tuningcited by 0