View-Invariant Policy Learning via Zero-Shot Novel View Synthesis
read the original abstract
Large-scale visuomotor policy learning is a promising approach toward developing generalizable manipulation systems. Yet, policies that can be deployed on diverse embodiments, environments, and observational modalities remain elusive. In this work, we investigate how knowledge from large-scale visual data of the world may be used to address one axis of variation for generalizable manipulation: observational viewpoint. Specifically, we study single-image novel view synthesis models, which learn 3D-aware scene-level priors by rendering images of the same scene from alternate camera viewpoints given a single input image. For practical application to diverse robotic data, these models must operate zero-shot, performing view synthesis on unseen tasks and environments. We empirically analyze view synthesis models within a simple data-augmentation scheme that we call View Synthesis Augmentation (VISTA) to understand their capabilities for learning viewpoint-invariant policies from single-viewpoint demonstration data. Upon evaluating the robustness of policies trained with our method to out-of-distribution camera viewpoints, we find that they outperform baselines in both simulated and real-world manipulation tasks. Videos and additional visualizations are available at https://s-tian.github.io/projects/vista.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
-
DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation
DockAnywhere lifts single demonstrations to diverse docking points via structure-preserving augmentation and point-cloud spatial editing to improve viewpoint generalization in visuomotor policies for mobile manipulation.
-
UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling
UniviewVLA generates multiview future views from two cameras via world modeling, plus token compression and view selection, to boost occlusion handling in robot manipulation while matching standard benchmark performance.
-
One Demo is Worth a Thousand Trajectories: Action-View Augmentation for Visuomotor Policies
A framework augments single fisheye demonstrations into multiple novel-view trajectories with obstacles via fisheye-adapted Gaussian Splatting and trajectory optimization, raising policy success rates in original and ...
-
WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations
WARPED synthesizes realistic wrist-view observations from monocular egocentric human videos via foundation models, hand-object tracking, retargeting, and Gaussian Splatting to train visuomotor policies that match tele...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.