Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Hao, Chen, Junyang, Pan, Jinshan, Dong, Jiangxin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915678695456768
author Chen, Hao
Chen, Junyang
Pan, Jinshan
Dong, Jiangxin
author_facet Chen, Hao
Chen, Junyang
Pan, Jinshan
Dong, Jiangxin
contents Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferior fidelity performance caused by the information loss from compression encoding of low-quality (LQ) inputs; (2) insufficient region-discriminative activation of generative priors; (3) misalignment between text prompts and their corresponding semantic regions. To address these limitations, we propose CODSR, a controllable one-step diffusion network for image super-resolution. First, we propose an LQ-guided feature modulation module that leverages original uncompressed information from LQ inputs to provide high-fidelity conditioning for the diffusion process. We then develop a region-adaptive generative prior activation method to effectively enhance perceptual richness without sacrificing local structural fidelity. Finally, we employ a text-matching guidance strategy to fully harness the conditioning potential of text prompts. Extensive experiments demonstrate that CODSR achieves superior perceptual quality and competitive fidelity compared with state-of-the-art methods with efficient one-step inference.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
Chen, Hao
Chen, Junyang
Pan, Jinshan
Dong, Jiangxin
Computer Vision and Pattern Recognition
Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferior fidelity performance caused by the information loss from compression encoding of low-quality (LQ) inputs; (2) insufficient region-discriminative activation of generative priors; (3) misalignment between text prompts and their corresponding semantic regions. To address these limitations, we propose CODSR, a controllable one-step diffusion network for image super-resolution. First, we propose an LQ-guided feature modulation module that leverages original uncompressed information from LQ inputs to provide high-fidelity conditioning for the diffusion process. We then develop a region-adaptive generative prior activation method to effectively enhance perceptual richness without sacrificing local structural fidelity. Finally, we employ a text-matching guidance strategy to fully harness the conditioning potential of text prompts. Extensive experiments demonstrate that CODSR achieves superior perceptual quality and competitive fidelity compared with state-of-the-art methods with efficient one-step inference.
title Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.14061