一步残差迁移扩散：基于蒸馏的图像超分辨率方法

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

March 17, 2025

作者: Daniil Selikhanovych, David Li, Aleksei Leonov, Nikita Gushchin, Sergei Kushneriuk, Alexander Filippov, Evgeny Burnaev, Iaroslav Koshelev, Alexander Korotin

cs.AI

摘要

超分辨率（SR）扩散模型虽能生成高质量的视觉结果，但需承担高昂的计算成本。尽管已有多种方法致力于加速基于扩散的SR模型，如SinSR等未能产生逼真的感知细节，而OSEDiff等则可能虚构出不存在的结构。为解决这些问题，我们提出了RSD，一种针对顶尖扩散SR模型ResShift的新蒸馏方法。该方法通过训练学生网络生成图像，使得基于这些图像训练的新伪ResShift模型能与教师模型保持一致。RSD实现了单步恢复，并大幅超越教师模型。我们证明，该蒸馏方法能够超越ResShift的另一蒸馏方法——SinSR，使其与最先进的基于扩散的SR蒸馏方法并驾齐驱。与基于预训练文本到图像模型的SR方法相比，RSD在感知质量上具有竞争力，生成的图像与退化输入图像对齐更佳，且所需参数和GPU内存更少。我们在包括RealSR、RealSet65、DRealSR、ImageNet和DIV2K在内的多种真实世界及合成数据集上提供了实验结果。

English

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate diffusion-based SR models, some (e.g., SinSR) fail to produce realistic perceptual details, while others (e.g., OSEDiff) may hallucinate non-existent structures. To overcome these issues, we present RSD, a new distillation method for ResShift, one of the top diffusion-based SR models. Our method is based on training the student network to produce such images that a new fake ResShift model trained on them will coincide with the teacher model. RSD achieves single-step restoration and outperforms the teacher by a large margin. We show that our distillation method can surpass the other distillation-based method for ResShift - SinSR - making it on par with state-of-the-art diffusion-based SR distillation methods. Compared to SR methods based on pre-trained text-to-image models, RSD produces competitive perceptual quality, provides images with better alignment to degraded input images, and requires fewer parameters and GPU memory. We provide experimental results on various real-world and synthetic datasets, including RealSR, RealSet65, DRealSR, ImageNet, and DIV2K.