InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies
cs.RO, cs.AI
Submitted: 2026-09-23
Updated: 2026-09-23
Project page: https://infi-nova.github.io
License: http://creativecommons.org/licenses/by/4.0/
The gist: Vision-Language-Action (VLA) policies often rely strongly on the camera viewpoints seen during training, causing substantial performance degradation when deployed from unseen perspectives.
Terminology
Abstract
Vision-Language-Action (VLA) policies often rely strongly on the camera viewpoints seen during training, causing substantial performance degradation when deployed from unseen perspectives. Collecting demonstrations from sufficiently diverse physical viewpoints is expensive and still provides only sparse coverage of the viewpoint space. We introduce InfiNoVA, a data-augmentation framework that converts synchronized multi-camera demonstrations into a dense distribution of geometrically consistent training views. InfiNoVA reconstructs each manipulation trajectory as a time-varying 3D Gaussian representation and renders novel observations from sampled camera poses while preserving the original state-action correspondence. This explicit scene representation improves frame-level fidelity and temporal consistency while reducing task-critical hallucinations observed in generative novel-view synthesis. Across four real-world manipulation tasks, policies trained with InfiNoVA achieve 5.4x higher average success under unseen randomized viewpoints than both VISTA-based augmentation and the unaugmented policy. InfiNoVA further achieves 1.7x higher success than training directly on all five physical camera views. These results show that dense, geometrically grounded viewpoint augmentation provides a practical route toward camera-robust robot policies without modifying the underlying policy architecture.
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
- AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
- InstantSplat: Sparse-view Gaussian Splatting in Seconds
- Octo: An Open-Source Generalist Robot Policy
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
- GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
- GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
- Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation
- RoboAug: One Annotation to Hundreds of Scenes via Region-Contrastive Data Augmentation for Robotic Manipulation
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies