mlsanityData to 14 Oct 2026

ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping

arXiv 2504.10857 ↗First posted 15 Apr 2025cs.RO cs.CVcited by 13

Not on the map. Why?

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.

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

64 of 81 references.

References · 64

  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  2. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  6. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  8. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  9. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  10. 2020Convolutional Occupancy Networkscited by 761
  11. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
38 more
  1. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  2. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  3. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  4. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  5. 2022Novel View Synthesis with Diffusion Modelscited by 300
  6. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  7. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  8. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
  9. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 264
  10. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  11. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  12. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 199
  13. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
  14. 2021ContactOpt: Optimizing Contact to Improve Graspscited by 139
  15. 2023Distilled Feature Fields Enable Few-Shot Language-Guided Manipulationcited by 130
  16. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 127
  17. 2018Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approachcited by 120
  18. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 117
  19. 2017Grasp Pose Detection in Point Cloudscited by 111
  20. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 108
  21. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 106
  22. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  23. 2023Neural Kernel Surface Reconstructioncited by 104
  24. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  25. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  26. 2018Jacquard: A Large Scale Dataset for Robotic Grasp Detectioncited by 87
  27. 2018PointNetGPD: Detecting Grasp Configurations from Point Setscited by 80
  28. 2016Shape Completion Enabled Robotic Graspingcited by 79
  29. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 72
  30. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  31. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 70
  32. 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objectscited by 64
  33. 2020EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulationcited by 61
  34. 2022HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarioscited by 53
  35. 2024Graspness Discovery in Clutters for Fast and Accurate Grasp Detectioncited by 48
  36. 2019Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completioncited by 43
  37. 2020Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completioncited by 33
  38. 2018ROI-based Robotic Grasp Detection for Object Overlapping Scenescited by 31

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 11.

13 papers.

Sort:

  1. 2026LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistencycited by 9
  2. 2026Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observationscited by 7
  3. 2026RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulationcited by 1
  4. 2026MessyKitchens: Contact-rich object-level 3D scene reconstructioncited by 1
  5. 2026GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priorscited by 1
  6. 2025SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuningcited by 0
  7. 2025SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streamscited by 0
  8. 2026A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimationcited by 0
  9. 2026Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observationscited by 0
  10. 2026GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectorscited by 0
  11. 2026RGS: Reflection-aware Gaussian Splatting via Learning Geometry Continuity for Reflective Objectscited by 0
  12. 2026CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Imagecited by 0
1 more
  1. 2026Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfoldingcited by 0