# XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution

Source: [XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution](<https://www.sota2.com/research/paper/68fa74321e209131cea6059c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:04:50.888Z

Authors: Yunpeng Qu, Kun Yuan, Kai Zhao, Qizhi Xie, Jinhua Hao, Ming Sun, Chao Zhou

Published: 2024-03-08T04:52:22.000Z

## Abstract

Diffusion-based methods, endowed with a formidable generative prior, have received increasing attention in Image Super-Resolution (ISR) recently. However, as low-resolution (LR) images often undergo severe degradation, it is challenging for ISR models to perceive the semantic and degradation information, resulting in restoration images with incorrect content or unrealistic artifacts. To address these issues, we propose a \\textit{Cross-modal Priors for Super-Resolution (XPSR)} framework. Within XPSR, to acquire precise and comprehensive semantic conditions for the diffusion model, cutting-edge Multimodal Large Language Models (MLLMs) are utilized. To facilitate better fusion of cross-modal priors, a \\textit{Semantic-Fusion Attention} is raised. To distill semantic-preserved information instead of undesired degradations, a \\textit{Degradation-Free Constraint} is attached between LR and its high-resolution (HR) counterpart. Quantitative and qualitative results show that XPSR is capable of generating high-fidelity and high-realism images across synthetic and real-world datasets. Codes are released at \\url{https://github.com/qyp2000/XPSR}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Real-world Super-Resolution on RealSR v1.0 (test)](<https://www.sota2.com/research/sota/real-world-super-resolution-on-realsr-v1-0-test.md>): Real-World Super-Resolution; RealSR v1.0 (test); PSNR: 18.99.

- [Real-world Super-Resolution on DIV2K real-world degradation (test)](<https://www.sota2.com/research/sota/real-world-super-resolution-on-div2k-real-world-degradation-test.md>): Real-World Super-Resolution; DIV2K real-world degradation (test); PSNR: 19.42.

- [Super-Resolution on Urban bicubic downsampling (test)](<https://www.sota2.com/research/sota/super-resolution-on-urban-bicubic-downsampling-test.md>): Super-Resolution; Urban bicubic downsampling (test); PSNR: 18.95.

- [Super-Resolution on DIV2K bicubic downsampling (test)](<https://www.sota2.com/research/sota/super-resolution-on-div2k-bicubic-downsampling-test.md>): Super-Resolution; DIV2K bicubic downsampling (test); PSNR: 20.25.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.05049>)

[PDF](<https://arxiv.org/pdf/2403.05049.pdf>)