mlsanityData to 14 Oct 2026

Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning

arXiv 2510.02268 ↗First posted 2 Oct 2025cs.RO cs.CVcited by 14

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics. Using Plucker embeddings of per-pixel rays, we show that conditioning on extrinsics significantly improves generalization across viewpoints for standard behavior cloning policies, including ACT, Diffusion Policy, and SmolVLA. To evaluate policy robustness under realistic viewpoint shifts, we introduce six manipulation tasks in RoboSuite and ManiSkill that pair "fixed" and "randomized" scene variants, decoupling background cues from camera pose. Our analysis reveals that policies without extrinsics often infer camera pose using visual cues from static backgrounds in fixed scenes; this shortcut collapses when workspace geometry or camera placement shifts. Conditioning on extrinsics restores performance and yields robust RGB-only control without depth. We release the tasks, demonstrations, and code at https://ripl.github.io/know_your_camera/ .

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 44 of its 57 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

44 of 57 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation7 Jul
  2. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning1 Jul
  3. 2023BridgeData V2: A Dataset for Robot Learning at Scale24 Aug
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
  5. 2022Behavior Transformers: Cloning k modes with one stone22 Jun
  6. 2021XIRL: Cross-embodiment Inverse Reinforcement Learning7 Jun

Other references · 38

  1. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  10. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  11. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  12. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
26 more
  1. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  2. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  3. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 423
  4. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  5. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  6. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 270
  7. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  8. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  9. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  10. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 138
  11. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  12. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  13. 2023GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fieldscited by 99
  14. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 80
  15. 2025Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulationcited by 48
  16. 2024RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learningcited by 46
  17. 2024Efficient Data Collection for Robotic Manipulation via Compositional Generalizationcited by 37
  18. 2024PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation Taskscited by 37
  19. 2024View-Invariant Policy Learning via Zero-Shot Novel View Synthesiscited by 35
  20. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  21. 2022Depth Field Networks for Generalizable Multi-view Scene Representationcited by 17
  22. 2023MoVie: Visual Model-Based Policy Adaptation for View Generalizationcited by 16
  23. 2024Point Cloud Models Improve Visual Robustness in Robotic Learnerscited by 14
  24. 2025CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulationcited by 11
  25. 2025EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulationcited by 9
  26. 2025FastMap: Revisiting Structure from Motion through First-Order Optimizationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  2. 2026Learning to Act Robustly with View-Invariant Latent Actionscited by 8
  3. 2026From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Modelcited by 3
  4. 2026Selective Cross-View Consistency for World Action Models: Held-Out Viewpoint Robustness Without Test-Time Camera Informationcited by 2
  5. 2026See like a Robot: Robot-Centric Pointmaps for VLA Modelscited by 1
  6. 2026Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policiescited by 1
  7. 2026AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulationcited by 0
  8. 2026Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?cited by 0
  9. 2026The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collectioncited by 0
  10. 2026RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learningcited by 0
  11. 2026AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attentioncited by 0
  12. 2026InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policiescited by 0
2 more
  1. 2026An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learningcited by 0
  2. 2026VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation
  2. 2026Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Camera
  3. 2026Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning
  4. 2024Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
  5. 2023One-Shot Imitation Learning: A Pose Estimation Perspective
  6. 2025Observer-Actor: Active Vision Imitation Learning with Sparse-View Gaussian Splatting
  7. 2026MatchingPolicy: Correspondence-Aware Policy Enables Cross-Object In-Context Learning
  8. 2021The Surprising Effectiveness of Representation Learning for Visual Imitation