We introduce RoLA, a framework that transforms any in-the-wild image into an interactive, physics-enabled robotic environment. Unlike previous methods, RoLA operates directly on a single image without requiring additional hardware or digital assets. Our framework democratizes robotic data generation by producing massive visuomotor robotic demonstrations within minutes from a wide range of image sources, including camera captures, robotic datasets, and Internet images. At its core, our approach combines a novel method for single-view physical scene recovery with an efficient visual blending strategy for photorealistic data collection. We demonstrate RoLA's versatility across applications like scalable robotic data generation and augmentation, robot learning from Internet images, and single-image real-to-sim-to-real systems for manipulators and humanoids. Video results are available at https://sihengz02.github.io/RoLA .
@article{arxiv.2509.22970,
title = {Robot Learning from Any Images},
author = {Siheng Zhao and Jiageng Mao and Wei Chow and Zeyu Shangguan and Tianheng Shi and Rong Xue and Yuxi Zheng and Yijia Weng and Yang You and Daniel Seita and Leonidas Guibas and Sergey Zakharov and Vitor Guizilini and Yue Wang},
journal= {arXiv preprint arXiv:2509.22970},
year = {2025}
}