Saved in:
Bibliographic Details
Main Authors: Kim, Aro, Jang, Myeongjin, Moon, Chaewon, Shin, Youngjin, Jeong, Jinwoo, Park, Sang-hyo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.02692
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Diffusion-based approaches have recently driven remarkable progress in real-world image super-resolution (SR). However, existing methods still struggle to simultaneously preserve fine details and ensure high-fidelity reconstruction, often resulting in suboptimal visual quality. In this paper, we propose FiDeSR, a high-fidelity and detail-preserving one-step diffusion super-resolution framework. During training, we introduce a detail-aware weighting strategy that adaptively emphasizes regions where the model exhibits higher prediction errors. During inference, low- and high-frequency adaptive enhancers further refine the reconstruction without requiring model retraining, enabling flexible enhancement control. To further improve the reconstruction accuracy, FiDeSR incorporates a residual-in-residual noise refinement, which corrects prediction errors in the diffusion noise and enhances fine detail recovery. FiDeSR achieves superior real-world SR performance compared to existing diffusion-based methods, producing outputs with both high perceptual quality and faithful content restoration. The source code will be released at: https://github.com/Ar0Kim/FiDeSR.