mlsanityData to 14 Oct 2026

Robot Learning from Any Images

arXiv 2509.22970 ↗First posted 26 Sep 2025cs.RO cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

We introduce RoLA, a framework that transforms any in-the-wild image into an interactive, physics-enabled robotic environment. Unlike previous methods, RoLA operates directly on a single image without requiring additional hardware or digital assets. Our framework democratizes robotic data generation by producing massive visuomotor robotic demonstrations within minutes from a wide range of image sources, including camera captures, robotic datasets, and Internet images. At its core, our approach combines a novel method for single-view physical scene recovery with an efficient visual blending strategy for photorealistic data collection. We demonstrate RoLA's versatility across applications like scalable robotic data generation and augmentation, robot learning from Internet images, and single-image real-to-sim-to-real systems for manipulators and humanoids. Video results are available at https://sihengz02.github.io/RoLA .

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 55 of its 65 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

55 of 65 references.

References · 55

  1. 2024Qwen2.5 Technical Reportcited by 4,942
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  5. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  6. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  7. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  8. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  9. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  10. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  11. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  12. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
38 more
  1. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
  2. 2023Learning Interactive Real-World Simulatorscited by 458
  3. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  4. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  5. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  6. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 218
  7. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 208
  8. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 189
  9. 2024PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generationcited by 174
  10. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 164
  11. 2022Human-to-Robot Imitation in the Wildcited by 161
  12. 2025PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understandingcited by 160
  13. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 156
  14. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 144
  15. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 125
  16. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 111
  17. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 106
  18. 2024Automated Creation of Digital Cousins for Robust Policy Learningcited by 91
  19. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 87
  20. 2025Phantom: Training Robots Without Robots Using Only Human Videoscited by 70
  21. 2024Real2Code: Reconstruct Articulated Objects via Code Generationcited by 69
  22. 2025PhysGen3D: Crafting a Miniature Interactive World from a Single Imagecited by 66
  23. 2024RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulationcited by 58
  24. 2024RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulatorcited by 53
  25. 2023cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generationcited by 52
  26. 2024Robo-GS: A Physics Consistent Spatial-Temporal Model for Robotic Arm with Hybrid Representationcited by 46
  27. 2024RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learningcited by 46
  28. 2025VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulationcited by 46
  29. 2025Re3Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulationcited by 43
  30. 2024Object-Centric Dexterous Manipulation from Human Motion Datacited by 41
  31. 2025RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generationcited by 40
  32. 2024Hand-Object Interaction Pretraining from Videoscited by 39
  33. 2025Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setupscited by 30
  34. 2024Learning from Massive Human Videos for Universal Humanoid Pose Controlcited by 29
  35. 2023AR2-D2:Training a Robot Without a Robotcited by 27
  36. 2024AutoVFX: Physically Realistic Video Editing from Natural Language Instructionscited by 27
  37. 2025Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videoscited by 26
  38. 2025VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotioncited by 22

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulationcited by 25
  2. 2025Robot Learning from a Physical World Modelcited by 20
  3. 2026Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Modelscited by 11
  4. 2025OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learningcited by 10
  5. 2026TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkourcited by 4
  6. 2025IGen: Scalable Data Generation for Robot Learning from Open-World Imagescited by 1
  7. 2026GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learningcited by 1