Metraipolis › archive › dc_b04dcdac2418
RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models — arXiv:2608.02953
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02953
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:58:06.694Z
- SHA-256 of the archived text
a0c28bb2f5add03884ba8821a9868fdaa90dfc6865762d13cc48c97dc4e92538- Stable URL of this page
https://metraipolis.com/documento/dc_b04dcdac2418
How to cite
RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models — arXiv:2608.02953 — arXiv (en), https://arxiv.org/abs/2608.02953 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b04dcdac2418 (Metraipolis archive dc_b04dcdac2418, sha256 a0c28bb2f5add03884ba8821a9868fdaa90dfc6865762d13cc48c97dc4e92538)
BibTeX
@misc{dcb04dcdac2418,
title = {RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models — arXiv:2608.02953},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02953},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b04dcdac2418; sha256 a0c28bb2f5add03884ba8821a9868fdaa90dfc6865762d13cc48c97dc4e92538},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02953. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Realistic weather translation is valuable for developing and evaluating autonomous driving systems, yet collecting paired videos of the same scenes under different weather conditions at scale is impractical. Existing methods therefore rely on synthetic data, 3D weather editing, or geometry-conditioned generation, often compromising weather realism or scene fidelity. We propose RealWeather, a driving world model for both realistic and scene-faithful weather translation. Our key idea is to learn authentic weather dynamics directly from real-world videos. Specifically, RealWeather employs Progressive Realism Bootstrapping, an iterative data-refinement strategy. Assisted by an auxiliary Pseudo-Clear Generation pipeline, training initially starts with pseudo-style conditioning videos. As training proceeds, these inputs are progressively replaced with increasingly realistic videos generated by the model itself. This strategy bridges the pseudo-to-real domain gap, allowing the model to adapt seamlessly to real-world input distributions and naturally support bidirectional clear adverse translation. Furthermore, to strictly enforce structural integrity and suppress hallucinations, we introduce Scene-Fidelity RL Optimization, a reward-driven policy optimization strategy that explicitly penalizes alterations to safety-critical driving elements. Extensive experiments demonstrate that RealWeather significantly outperforms existing methods in visual realism and structural preservation, while enabling robust long-tail weather scenario generation and strong zero-shot out-of-distribution generalization. Our video demos can be found at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.02953 — 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 2026-10-31T12:45:33.204Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).