{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:44:29Z","timestamp":1773801869752,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Pre-trained diffusion models have shown great potential in real-world image super-resolution (Real-ISR) tasks by enabling high-resolution reconstructions. While one-step diffusion (OSD) methods significantly improve efficiency compared to traditional multi-step approaches, they still have limitations in balancing fidelity and realism across diverse scenarios. Since the OSDs for SR are usually trained or distilled by a single timestep, they lack flexible control mechanisms to adaptively prioritize these competing objectives, which are inherently manageable in multi-step methods through adjusting sampling steps. To address this challenge, we propose a Realism Controlled One-step Diffusion (RCOD) framework for Real-ISR. RCOD provides a latent domain grouping strategy that enables explicit control over fidelity-realism trade-offs during the noise prediction phase with minimal training paradigm modifications and original training data. A degradation-aware sampling strategy is also introduced to align distillation regularization with the grouping strategy and enhance the controlling of trade-offs. Moreover, a visual prompt injection module is used to replace conventional text prompts with degradation-aware visual tokens, enhancing both restoration accuracy and semantic consistency. Our method achieves superior fidelity and perceptual quality while maintaining computational efficiency. Extensive experiments demonstrate that RCOD outperforms state-of-the-art OSD methods in both quantitative metrics and visual qualities, with flexible realism control capabilities in the inference stage.<\/jats:p>","DOI":"10.1609\/aaai.v40i13.38067","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:03:29Z","timestamp":1773792209000},"page":"10906-10914","source":"Crossref","is-referenced-by-count":0,"title":["Realism Control One-step Diffusion for Real-world Image Super Resolution"],"prefix":"10.1609","volume":"40","author":[{"given":"Zongliang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siming","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng-Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38067\/42029","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38067\/42029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:03:30Z","timestamp":1773792210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i13.38067","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}