{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stem-ob-generalizable-visual-imitation","title":"Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion","arxiv_id":"2411.04919","date":"2024-11-07","proceeding":null,"authors":["Kaizhe Hu","Zihang Rui","Yao He","Yuyao Liu","Pu Hua","Huazhe Xu"],"abstract":"Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences while maintaining high-level scene structures. This image inversion process is akin to transforming the observation into a shared representation, from which other observations stem, with extraneous details removed. Stem-OB contrasts with data-augmentation approaches as it is robust to various unspecified appearance changes without the need for additional training. Our method is a simple yet highly effective plug-and-play solution. Empirical results confirm the effectiveness of our approach in simulated tasks and show an exceptionally significant improvement in real-world applications, with an average increase of 22.2% in success rates compared to the best baseline. See https://hukz18.github.io/Stem-Ob/ for more info.","url_abs":"https://arxiv.org/abs/2411.04919v2","url_pdf":"https://arxiv.org/pdf/2411.04919v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"stem-ob-generalizable-visual-imitation","repo_url":"https://github.com/hukz18/Stem-Ob-Code","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.04919","atlas_url":"https://app.syntology.ai/?focus=2411.04919","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}