FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution

2026-03-03

AI Summary

This work addresses the challenge of simultaneously achieving high fidelity and fine detail preservation in real-world image super-resolution with diffusion models. To this end, we propose a one-step diffusion-based super-resolution framework that integrates a detail-aware weighted training strategy, a low-/high-frequency adaptive enhancer, and a residual nested noise refinement mechanism. Our method enables flexible enhancement of reconstruction quality without requiring retraining, significantly improving visual details while maintaining content fidelity. Extensive experiments demonstrate that the proposed approach substantially outperforms existing diffusion-based methods on real-image super-resolution benchmarks, successfully unifying perceptual quality and reconstruction accuracy.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• super-resolution
• diffusion model
• high-fidelity
• detail preservation
• real-world image

Innovation

• diffusion super-resolution
• detail-preserving
• one-step diffusion
• adaptive enhancement
• noise refinement