OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs

TL;DR

OFTSR introduces a one-step, flow-based super-resolution method that allows flexible tuning between image fidelity and realism, achieving state-of-the-art results with minimal computational cost.

Contribution

The paper presents a novel one-step super-resolution framework with tunable fidelity-realism trade-offs, using a teacher-student distillation approach aligned on the same sampling trajectory.

Findings

Achieves state-of-the-art one-step super-resolution performance.

Enables flexible control over fidelity and realism levels.

Operates efficiently with a single prediction step.

Abstract

Recent advances in diffusion and flow-based generative models have demonstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods either require numerous sampling steps to generate high-quality images, resulting in significant computational overhead, or rely on common model distillation, which usually imposes a fixed fidelity-realism trade-off and thus lacks flexibility. In this paper, we introduce OFTSR, a novel flow-based framework for one-step image super-resolution that can produce outputs with tunable levels of fidelity and realism. Our approach first trains a conditional flow-based super-resolution model to serve as a teacher model. We then distill this teacher model by applying a specialized constraint. Specifically, we force the predictions from our one-step student model for same input to lie on the same sampling ODE trajectory of the teacher model. This alignment ensures that the student model's single-step predictions from initial states match the teacher's predictions from a closer intermediate state. Through extensive experiments on datasets including FFHQ (256$\times$256), DIV2K, and ImageNet (256$\times$256), we demonstrate that OFTSR achieves state-of-the-art performance for one-step image super-resolution, while having the ability to flexibly tune the fidelity-realism trade-off. Codes: \href{https://github.com/yuanzhi-zhu/OFTSR}{https://github.com/yuanzhi-zhu/OFTSR}.