Metraipolis › archive › dc_bb4d3a3da535

ODDR: One-Step Deshadow Diffusion via Reward Guidance — arXiv:2610.01291

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01291
License (as archived)
CC0-1.0
Archived
2026-10-06T19:13:14.563Z
SHA-256 of the archived text
b5ae2fd0ffe73a2117baf563c7676c8ddc7649389321a65ac5bccfddd6ef9648
Stable URL of this page
https://metraipolis.com/documento/dc_bb4d3a3da535

How to cite

ODDR: One-Step Deshadow Diffusion via Reward Guidance — arXiv:2610.01291 — arXiv (en), https://arxiv.org/abs/2610.01291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb4d3a3da535 (Metraipolis archive dc_bb4d3a3da535, sha256 b5ae2fd0ffe73a2117baf563c7676c8ddc7649389321a65ac5bccfddd6ef9648)
BibTeX
@misc{dcbb4d3a3da535,
  title = {ODDR: One-Step Deshadow Diffusion via Reward Guidance — arXiv:2610.01291},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01291},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb4d3a3da535; sha256 b5ae2fd0ffe73a2117baf563c7676c8ddc7649389321a65ac5bccfddd6ef9648},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in deep learning for shadow removal have significantly enhanced image quality and realism. However, most approaches rely on real-world paired datasets, which are costly to collect and often limited in scene diversity, leading to limited generalization. To address these limitations, we propose One-step Deshadow Diffusion via Reward guidance (ODDR), a new framework that achieves efficient and high-fidelity shadow removal without relying on real-world paired supervision. Our method begins with One-step Deshadow Diffusion (ODD), a baseline model trained on synthetic shadow data for efficient one-step shadow-free reconstruction. We further adapt ODD into ODDR using ShadowReward. In contrast to traditional, annotation-heavy approaches, ShadowReward is the first reward model for shadow removal trained entirely without human annotation. It learns to mimic human perceptual judgments by ranking synthetically generated images with controlled degradations, such as texture distortion and boundary artifacts. This reward-guided fine-tuning enables ODDR to close the synthetic-to-real domain gap. Extensive experiments show that ODD achieves strong performance without relying on real-world paired supervision, and ODDR further improves the results, narrowing the gap to fully supervised methods trained on real-world paired data while maintaining higher computational efficiency as a single-step model.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.01291 — 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 2026-10-06T17:37:36.773Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).