mlsanityData to 14 Oct 2026

GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation

arXiv 2509.15733 ↗First posted 19 Sep 2025cs.RO cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D geometry-aware robotic manipulation policy that leverages multi-view input. GP3 employs a spatial encoder to infer dense spatial features from RGB observations, which enable the estimation of depth and camera parameters, leading to a compact yet expressive 3D scene representation tailored for manipulation. This representation is fused with language instructions and translated into continuous actions via a lightweight policy head. Comprehensive experiments demonstrate that GP3 consistently outperforms state-of-the-art methods on simulated benchmarks. Furthermore, GP3 transfers effectively to real-world robots without depth sensors or pre-mapped environments, requiring only minimal fine-tuning. These results highlight GP3 as a practical, sensor-agnostic solution for geometry-aware robotic manipulation.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 57 of its 70 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

57 of 70 references.

References · 57

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  11. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
38 more
  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  3. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  4. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  5. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  6. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  7. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  8. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  9. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  10. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  11. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  12. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  13. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 353
  14. 2017Deep Reinforcement Learning: An Overviewcited by 333
  15. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  16. 20243D Reconstruction with Spatial Memorycited by 277
  17. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  18. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 218
  19. 2024Global Structure-from-Motion Revisitedcited by 218
  20. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 208
  21. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  22. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  23. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 138
  24. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  25. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 121
  26. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 103
  27. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  28. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 80
  29. 2024Theia: Distilling Diverse Vision Foundation Models for Robot Learningcited by 61
  30. 2023Online Map Vectorization for Autonomous Driving: A Rasterization Perspectivecited by 54
  31. 2025Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulationcited by 47
  32. 2024Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulationcited by 46
  33. 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learningcited by 45
  34. 2024PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation Taskscited by 37
  35. 2025FP3: A 3D Foundation Policy for Robotic Manipulationcited by 32
  36. 2024SPA: 3D Spatial-Awareness Enables Effective Embodied Representationcited by 28
  37. 2024SUGAR: Pre-training 3D Visual Representations for Roboticscited by 26
  38. 2024VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulationcited by 21

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 10.

12 papers.

  1. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  2. 2025StereoVLA: Enhancing Vision-Language-Action Models with Stereo Visioncited by 18
  3. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 16
  4. 2026Geometric Action Model for Robot Policy Learningcited by 11
  5. 2026Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulationcited by 5
  6. 2026From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Modelcited by 3
  7. 2026R3DP: Real-Time 3D-Aware Policy for Embodied Manipulationcited by 2
  8. 2026R3D: Revisiting 3D Policy Learningcited by 1
  9. 2026GeoProp: Grounding Robot State in Vision for Generalist Manipulationcited by 1
  10. 2026Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Modelscited by 0
  11. 2026VGM-VS: Rethinking Visual Geometry Model for High-Precision Visual Servoingcited by 0
  12. 2026GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Modelscited by 0