Fast Image Super-Resolution via Consistency Rectified Flow

TL;DR

FlowSR is a novel single-step super-resolution method that reformulates the task as a rectified flow, improving efficiency and quality by leveraging consistency learning and a dual-scheduler strategy.

Contribution

The paper introduces FlowSR, a new approach that uses a rectified flow and improved consistency learning for fast, high-quality image super-resolution.

Findings

FlowSR achieves state-of-the-art efficiency in super-resolution.

FlowSR produces high-fidelity images with fine textures.

The dual-scheduler strategy enhances both speed and detail recovery.

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.