FlowIE: Efficient Image Enhancement via Rectified Flow

TL;DR

FlowIE introduces a flow-based image enhancement framework that significantly accelerates inference and improves robustness by employing rectified flow to efficiently transform images from low to high quality.

Contribution

The paper proposes FlowIE, a novel rectified flow method that speeds up image enhancement inference and leverages pre-trained diffusion models for diverse real-world applications.

Findings

Achieves faster inference with fewer than 5 steps.

Demonstrates superior enhancement quality on synthetic and real datasets.

Outperforms existing diffusion-based methods in robustness and efficiency.

Abstract

Image enhancement holds extensive applications in real-world scenarios due to complex environments and limitations of imaging devices. Conventional methods are often constrained by their tailored models, resulting in diminished robustness when confronted with challenging degradation conditions. In response, we propose FlowIE, a simple yet highly effective flow-based image enhancement framework that estimates straight-line paths from an elementary distribution to high-quality images. Unlike previous diffusion-based methods that suffer from long-time inference, FlowIE constructs a linear many-to-one transport mapping via conditioned rectified flow. The rectification straightens the trajectories of probability transfer, accelerating inference by an order of magnitude. This design enables our FlowIE to fully exploit rich knowledge in the pre-trained diffusion model, rendering it well-suited for various real-world applications. Moreover, we devise a faster inference algorithm, inspired by Lagrange's Mean Value Theorem, harnessing midpoint tangent direction to optimize path estimation, ultimately yielding visually superior results. Thanks to these designs, our FlowIE adeptly manages a diverse range of enhancement tasks within a concise sequence of fewer than 5 steps. Our contributions are rigorously validated through comprehensive experiments on synthetic and real-world datasets, unveiling the compelling efficacy and efficiency of our proposed FlowIE. Code is available at https://github.com/EternalEvan/FlowIE.