Fast Image Super-Resolution via Consistency Rectified Flow

2026-05-12

AI Summary

This work addresses the inefficiency of existing diffusion models in image super-resolution, which typically rely on multi-step sampling, and the difficulty faced by single- or few-step approaches in simultaneously achieving high reconstruction accuracy and fine detail fidelity. To overcome these limitations, the paper formulates super-resolution as a correction flow from low- to high-resolution images and introduces a consistency distillation mechanism augmented with high-resolution regularization. Furthermore, a dual fast-slow scheduling strategy is devised to optimize the one-step generation process. The proposed method significantly enhances both reconstruction quality and texture detail recovery while requiring only a single inference step, thereby achieving a synergistic balance between computational efficiency and performance.

Abstract

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.

Problem

• image super-resolution
• diffusion models
• single-step generation
• consistency learning
• reconstruction fidelity

Innovation

• rectified flow
• consistency learning
• image super-resolution
• single-step generation
• fast-slow scheduling