Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning

TL;DR

This paper presents a scalable method that uses multiple synchronized camera views during demonstration collection to improve data efficiency and generalization in robot imitation learning, without extra human effort.

Contribution

It introduces a framework leveraging inherent scene diversity through camera view scaling and a multiview action aggregation method for single-view policies.

Findings

Significant improvements in data efficiency over single-view baselines.

Enhanced viewpoint invariance in visual representations.

Effective multiview action aggregation during deployment.

Abstract

The generalization ability of imitation learning policies for robotic manipulation is fundamentally constrained by the diversity of expert demonstrations, while collecting demonstrations across varied environments is costly and difficult in practice. In this paper, we propose a practical framework that exploits inherent scene diversity without additional human effort by scaling camera views during demonstration collection. Instead of acquiring more trajectories, multiple synchronized camera perspectives are used to generate pseudo-demonstrations from each expert trajectory, which enriches the training distribution and improves viewpoint invariance in visual representations. We analyze how different action spaces interact with view scaling and show that camera-space representations further enhance diversity. In addition, we introduce a multiview action aggregation method that allows single-view policies to benefit from multiple cameras during deployment. Extensive experiments in simulation and real-world manipulation tasks demonstrate significant gains in data efficiency and generalization compared to single-view baselines. Our results suggest that scaling camera views provides a practical and scalable solution for imitation learning, which requires minimal additional hardware setup and integrates seamlessly with existing imitation learning algorithms. The website of our project is https://yichen928.github.io/robot_multiview.