{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T02:06:35Z","timestamp":1768701995838,"version":"3.49.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Diffusion-based image super-resolution (SR) methods have demonstrated remarkable performance. Recent advancements have introduced deterministic sampling processes that reduce inference from 15 iterative steps to a single step, thereby significantly improving the inference speed of existing diffusion models. However, their efficiency remains limited when handling complex semantic regions due to the single-step inference.\n\nTo address this limitation, we propose SAMSR, a semantic-guided diffusion framework that incorporates semantic segmentation masks into the sampling process. Specifically, we introduce the SAM-Noise Module, which refines Gaussian noise using segmentation masks to preserve spatial and semantic features. Furthermore, we develop a pixel-wise sampling strategy that dynamically adjusts the residual transfer rate and noise strength based on pixel-level semantic weights, prioritizing semantically rich regions during the diffusion process. To enhance model training, we also propose a semantic consistency loss, which aligns pixel-wise semantic weights between predictions and ground truth.\n\nExtensive experiments on both real-world and synthetic datasets demonstrate that SAMSR significantly improves perceptual quality and detail recovery, particularly in semantically complex images.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/186","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"1666-1674","source":"Crossref","is-referenced-by-count":1,"title":["Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution"],"prefix":"10.24963","author":[{"given":"Zihang","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}]}],"member":"10584","event":{"name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2025","number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2025,8,16]]},"end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:33:14Z","timestamp":1758627194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/186"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/186","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}