Paper ID: 2411.18662

HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Prior

Li-Yuan Tsao, Hao-Wei Chen, Hao-Wei Chung, Deqing Sun, Chun-Yi Lee, Kelvin C.K. Chan, Ming-Hsuan Yang

Text-to-image diffusion models have emerged as powerful priors for real-world image super-resolution (Real-ISR). However, existing methods may produce unintended results due to noisy text prompts and their lack of spatial information. In this paper, we present HoliSDiP, a framework that leverages semantic segmentation to provide both precise textual and spatial guidance for diffusion-based Real-ISR. Our method employs semantic labels as concise text prompts while introducing dense semantic guidance through segmentation masks and our proposed Segmentation-CLIP Map. Extensive experiments demonstrate that HoliSDiP achieves significant improvement in image quality across various Real-ISR scenarios through reduced prompt noise and enhanced spatial control.

Submitted: Nov 27, 2024