# Grasp Diffusion Network: Learning Grasp Generators from Partial Point Clouds with Diffusion Models in SO(3)xR3

arXiv: https://arxiv.org/abs/2412.08398 · HTML: https://mlsanity.com/paper/2412.08398/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Goal-Conditioned Imitation Learning using Score-based Diffusion Policies](https://mlsanity.com/paper/2304.02532/) (2023)
- [Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes](https://mlsanity.com/paper/2103.14127/) (2021)
- [ACRONYM: A Large-Scale Grasp Dataset Based on Simulation](https://mlsanity.com/paper/2011.09584/) (2020)
- [Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study](https://mlsanity.com/paper/1404.3785/) (2014)
- [Deep Learning Approaches to Grasp Synthesis: A Review](https://mlsanity.com/paper/2207.02556/) (2022)
- [6-DOF Grasping for Target-driven Object Manipulation in Clutter](https://mlsanity.com/paper/1912.03628/) (2019)
- [Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations](https://mlsanity.com/paper/2408.04380/) (2024)
- [GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models](https://mlsanity.com/paper/2312.11243/) (2023)
- [Grasp Learning: Models, Methods, and Performance](https://mlsanity.com/paper/2211.04895/) (2022)

## Built on by (most cited first, 4 of 4)

- [Diffusion Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2504.08438/) (2025)
- [GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training](https://mlsanity.com/paper/2507.13097/) (2025)
- [Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization](https://mlsanity.com/paper/2504.09927/) (2025)
- [Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control](https://mlsanity.com/paper/2509.06201/) (2025)

## Abstract (arXiv)

Grasping objects successfully from a single-view camera is crucial in many robot manipulation tasks. An approach to solve this problem is to leverage simulation to create large datasets of pairs of objects and grasp poses, and then learn a conditional generative model that can be prompted quickly during deployment. However, the grasp pose data is highly multimodal since there are several ways to grasp an object. Hence, in this work, we learn a grasp generative model with diffusion models to sample candidate grasp poses given a partial point cloud of an object. A novel aspect of our method is to consider diffusion in the manifold space of rotations and to propose a collision-avoidance cost guidance to improve the grasp success rate during inference. To accelerate grasp sampling we use recent techniques from the diffusion literature to achieve faster inference times. We show in simulation and real-world experiments that our approach can grasp several objects from raw depth images with 90% success rate and benchmark it against several baselines.