# ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping

arXiv: https://arxiv.org/abs/2504.10857 · HTML: https://mlsanity.com/paper/2504.10857/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 81 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Builds on (most cited first, 30 of 64)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [Novel View Synthesis with Diffusion Models](https://mlsanity.com/paper/2210.04628/) (2022)
- [SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation](https://mlsanity.com/paper/2212.04493/) (2022)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://mlsanity.com/paper/2203.09516/) (2022)
- [MeshDiffusion: Score-based Generative 3D Mesh Modeling](https://mlsanity.com/paper/2303.08133/) (2023)
- [XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies](https://mlsanity.com/paper/2312.03806/) (2023)
- [ContactOpt: Optimizing Contact to Improve Grasps](https://mlsanity.com/paper/2104.07267/) (2021)
- [Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation](https://mlsanity.com/paper/2308.07931/) (2023)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [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)

## Built on by (most cited first, 13 of 13)

- [LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency](https://mlsanity.com/paper/2602.18735/) (2026)
- [Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations](https://mlsanity.com/paper/2604.27106/) (2026)
- [RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation](https://mlsanity.com/paper/2603.14880/) (2026)
- [MessyKitchens: Contact-rich object-level 3D scene reconstruction](https://mlsanity.com/paper/2603.16868/) (2026)
- [GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors](https://mlsanity.com/paper/2606.08440/) (2026)
- [SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning](https://mlsanity.com/paper/2506.23835/) (2025)
- [SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streams](https://mlsanity.com/paper/2510.10602/) (2025)
- [A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation](https://mlsanity.com/paper/2606.06878/) (2026)
- [Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations](https://mlsanity.com/paper/2607.00498/) (2026)
- [GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors](https://mlsanity.com/paper/2608.00946/) (2026)
- [RGS: Reflection-aware Gaussian Splatting via Learning Geometry Continuity for Reflective Objects](https://mlsanity.com/paper/2609.19421/) (2026)
- [CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image](https://mlsanity.com/paper/2609.25654/) (2026)
- [Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding](https://mlsanity.com/paper/2609.31452/) (2026)

## Abstract (arXiv)

Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these issues, we introduce ZeroGrasp, a novel framework that simultaneously performs 3D reconstruction and grasp pose prediction in near real-time. A key insight of our method is that occlusion reasoning and modeling the spatial relationships between objects is beneficial for both accurate reconstruction and grasping. We couple our method with a novel large-scale synthetic dataset, which comprises 1M photo-realistic images, high-resolution 3D reconstructions and 11.3B physically-valid grasp pose annotations for 12K objects from the Objaverse-LVIS dataset. We evaluate ZeroGrasp on the GraspNet-1B benchmark as well as through real-world robot experiments. ZeroGrasp achieves state-of-the-art performance and generalizes to novel real-world objects by leveraging synthetic data.