SOURCE-LINKED INTELLIGENCE

InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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 rep

Read original source ↗ Open in workspace

recordType

paper

region

Global