Fast Image Super-Resolution via Consistency Rectified Flow

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Jiaqi, Li, Wenbo, Sun, Haoze, Li, Fan, Wang, Zhixin, Peng, Long, Ren, Jingjing, Yang, Haoran, Hu, Xiaowei, Pei, Renjing, Heng, Pheng-Ann
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917554722701312
author Xu, Jiaqi
Li, Wenbo
Sun, Haoze
Li, Fan
Wang, Zhixin
Peng, Long
Ren, Jingjing
Yang, Haoran
Hu, Xiaowei
Pei, Renjing
Heng, Pheng-Ann
author_facet Xu, Jiaqi
Li, Wenbo
Sun, Haoze
Li, Fan
Wang, Zhixin
Peng, Long
Ren, Jingjing
Yang, Haoran
Hu, Xiaowei
Pei, Renjing
Heng, Pheng-Ann
contents Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders their practical applications. While recent efforts have introduced few- or single-step solutions, existing methods either inefficiently model the process from noisy input or fail to fully exploit iterative generative priors, compromising the fidelity and quality of the reconstructed images. To address this issue, we propose FlowSR, a novel approach that reformulates the SR problem as a rectified flow from low-resolution (LR) to high-resolution (HR) images. Our method leverages an improved consistency learning strategy to enable high-quality SR in a single step. Specifically, we refine the original consistency distillation process by incorporating HR regularization, ensuring that the learned SR flow not only enforces self-consistency but also converges precisely to the ground-truth HR target. Furthermore, we introduce a fast-slow scheduling strategy, where adjacent timesteps for consistency learning are sampled from two distinct schedulers: a fast scheduler with fewer timesteps to improve efficiency, and a slow scheduler with more timesteps to capture fine-grained texture details. Extensive experiments demonstrate that FlowSR achieves outstanding performance in both efficiency and image quality. Code: \href{https://github.com/jiaqixuac/FlowSR}{this https URL}.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12377
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fast Image Super-Resolution via Consistency Rectified Flow
Xu, Jiaqi
Li, Wenbo
Sun, Haoze
Li, Fan
Wang, Zhixin
Peng, Long
Ren, Jingjing
Yang, Haoran
Hu, Xiaowei
Pei, Renjing
Heng, Pheng-Ann
Computer Vision and Pattern Recognition
Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders their practical applications. While recent efforts have introduced few- or single-step solutions, existing methods either inefficiently model the process from noisy input or fail to fully exploit iterative generative priors, compromising the fidelity and quality of the reconstructed images. To address this issue, we propose FlowSR, a novel approach that reformulates the SR problem as a rectified flow from low-resolution (LR) to high-resolution (HR) images. Our method leverages an improved consistency learning strategy to enable high-quality SR in a single step. Specifically, we refine the original consistency distillation process by incorporating HR regularization, ensuring that the learned SR flow not only enforces self-consistency but also converges precisely to the ground-truth HR target. Furthermore, we introduce a fast-slow scheduling strategy, where adjacent timesteps for consistency learning are sampled from two distinct schedulers: a fast scheduler with fewer timesteps to improve efficiency, and a slow scheduler with more timesteps to capture fine-grained texture details. Extensive experiments demonstrate that FlowSR achieves outstanding performance in both efficiency and image quality. Code: \href{https://github.com/jiaqixuac/FlowSR}{this https URL}.
title Fast Image Super-Resolution via Consistency Rectified Flow
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12377