Metraipolis › archive › dc_fc7d72d0720e
ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning — arXiv:2609.19661
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19661
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:25:29.478Z
- SHA-256 of the archived text
e083a2e6c0aeafb04bc17014c43680c65e9a726f58af4e803836a8a8bbff9138- Stable URL of this page
https://metraipolis.com/documento/dc_fc7d72d0720e
How to cite
ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning — arXiv:2609.19661 — arXiv (en), https://arxiv.org/abs/2609.19661 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc7d72d0720e (Metraipolis archive dc_fc7d72d0720e, sha256 e083a2e6c0aeafb04bc17014c43680c65e9a726f58af4e803836a8a8bbff9138)
BibTeX
@misc{dcfc7d72d0720e,
title = {ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning — arXiv:2609.19661},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19661},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc7d72d0720e; sha256 e083a2e6c0aeafb04bc17014c43680c65e9a726f58af4e803836a8a8bbff9138},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19661. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Imitation-learned robot policies are frequently overfit to the visual conditions present in their training demonstrations. Consequently, variations in object color or background appearance often induce substantial performance degradation. A common mitigation strategy is to acquire additional demonstrations in each novel visual context; however, this approach is resource-intensive, requiring repeated access to a robot, a controlled environment, and human operation for every appearance condition to be covered. We introduce ReShoot, a framework that synthesizes visual diversity by re-rendering previously recorded demonstrations under altered appearances, thereby shifting the burden from data collection to generation. A vision-language model captions the scene, edits a targeted attribute (e.g., background, object color, or material), and an edge-conditioned video generator re-renders both camera views to match. The instruction is updated accordingly. The action sequence and proprioceptive trajectory are copied verbatim without relabeling, so each generated episode retains the recorded action and proprioceptive labels. On LIBERO, a policy trained on an equal mixture of recorded and re-rendered demonstrations matches the performance of recorded-only training (96.5% vs. 96.9%). Moreover, the mixed training set improves robustness to scene perturbations on LIBERO-Plus (85.5% vs. 82.3%). Across two physical robotic platforms, deploying ReShoot with 43 and 100 pre-collected demonstrations increased the success rate on recolored objects from 0.0% to 42.9% and 47.5%, respectively, while maintaining performance under the original recorded appearance. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.19661 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T04:47:38.840Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).