# GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors

arXiv: https://arxiv.org/abs/2606.08440 · HTML: https://mlsanity.com/paper/2606.08440/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 76 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 30 of 67)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model](https://mlsanity.com/paper/2310.15110/) (2023)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [TripoSR: Fast 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/2403.02151/) (2024)
- [Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes](https://mlsanity.com/paper/2103.14127/) (2021)
- [MeshDiffusion: Score-based Generative 3D Mesh Modeling](https://mlsanity.com/paper/2303.08133/) (2023)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching](https://mlsanity.com/paper/1710.01330/) (2017)
- [GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data](https://mlsanity.com/paper/2505.03233/) (2025)
- [Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach](https://mlsanity.com/paper/1804.05172/) (2018)
- [ACRONYM: A Large-Scale Grasp Dataset Based on Simulation](https://mlsanity.com/paper/2011.09584/) (2020)
- [RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos](https://mlsanity.com/paper/2401.12592/) (2024)
- [Grasp Pose Detection in Point Clouds](https://mlsanity.com/paper/1706.09911/) (2017)
- [textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Driving](https://mlsanity.com/paper/2405.20323/) (2024)
- [Neural Kernel Surface Reconstruction](https://mlsanity.com/paper/2305.19590/) (2023)
- [Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model](https://mlsanity.com/paper/2410.13882/) (2024)
- [PointNetGPD: Detecting Grasp Configurations from Point Sets](https://mlsanity.com/paper/1809.06267/) (2018)
- [Deep Learning Approaches to Grasp Synthesis: A Review](https://mlsanity.com/paper/2207.02556/) (2022)

## Built on by (most cited first, 1 of 1)

- [CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image](https://mlsanity.com/paper/2609.25654/) (2026)

## Abstract (arXiv)

Robotic grasping is a fundamental capability in robotic manipulation. Yet grasping remains challenging under partial observations. Reliable grasping depends on both local contact cues and object-level 3D structure. Existing geometry-aware grasping methods recognize the value of reconstruction, but they typically treat geometry as an intermediate prediction rather than a reusable object prior for grasping. In this paper, we present GraspFoM, a unified framework that leverages 3D foundation priors (SAM3D) to build a shared 3D object latent for both reconstruction and grasp pose prediction. Built on this shared object latent, we introduce an anchor-initialized truncated pose-reasoning diffuser that predicts continuous and multimodal grasp poses without directly relying on discrete grasp candidates. We further investigate the interaction between reconstruction and grasping through a reconstruction-aware scorer and a residual latent updater. Reconstruction provides grounded geometric cues, while grasp supervision refines the shared object latent toward grasp-relevant affordances. GraspFoM jointly predicts grasp poses and reconstructs high-fidelity 3D assets in mesh and 3DGS forms. Comprehensive experiments demonstrate that GraspFoM achieves state-of-the-art results on both reconstruction and grasping. Notably, these improvements require only a small number of additional trainable parameters. Component-wise ablation studies also demonstrate the contribution of each component.