{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:59Z","timestamp":1758672899945,"version":"3.44.0"},"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>Image super-resolution (ISR) is a classic and challenging problem in computer vision because of complex and unknown degradation patterns in the data collection process. Leveraging powerful generative priors, diffusion-based methods have recently established new state-of-the-art ISR performance, but their characteristics in the frequency domain are still underexplored. In this paper, we innovatively investigate their frequency-domain behaviors from a sampling timestep perspective. Experimentally, we find that current diffusion-based ISR algorithms exhibit insufficiency in different frequency components in distinct groups of timesteps during the sampling. To address this, we first propose a Timestep Division Controller that is able to adaptively divide the timesteps into groups based on the performance gradient across different components. Next, we design two dedicated modules --- the Amplitude and Phase Enhancement Module (APEM) and the High- and Low-Frequency Enhancement Module (HLEM), to regulate the information flow of distinct frequency-domain features. By adaptively enhancing specific frequency components at different stages of the sampling process, the two modules effectively compensate for the insufficient frequency-domain perception of diffusion-based ISR models. Extensive experiments on three benchmark datasets verify the superior ISR performance of our method, e.g., achieving an average 5.40% improvement on CLIP-IQA compared to the best diffusion-based ISR baseline.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/168","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"1503-1511","source":"Crossref","is-referenced-by-count":0,"title":["A Timestep-Adaptive Frequency-Enhancement Framework for Diffusion-based Image Super-Resolution"],"prefix":"10.24963","author":[{"given":"Yueying","family":"Li","sequence":"first","affiliation":[{"name":"School of Software Technology, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqing","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance, Hangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guozhi","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance, Hangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlei","family":"Hu","sequence":"additional","affiliation":[{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"},{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"},{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","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":"2025-09-23T11:33:11Z","timestamp":1758627191000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/168"}},"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\/168","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}