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. Our method is based on training the student network to produce images such 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 noticeable margin in various perceptual metrics (LPIPS, CLIPIQA, MUSIQ). We show that our distillation method can surpass SinSR, the other distillation-based method for ResShift, making it on par with state-of-the-art diffusion SR distillation methods with limited computational costs in terms of perceptual quality. Compared to SR methods based on pre-trained text-to-image models, RSD produces competitive perceptual quality and requires fewer parameters, GPU memory, and training cost. We provide experimental results on various real-world and synthetic datasets, including RealSR, RealSet65, DRealSR, ImageNet, and DIV2K.
@article{arxiv.2503.13358,
title = {One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation},
author = {Daniil Selikhanovych and David Li and Aleksei Leonov and Nikita Gushchin and Sergei Kushneriuk and Alexander Filippov and Evgeny Burnaev and Iaroslav Koshelev and Alexander Korotin},
journal= {arXiv preprint arXiv:2503.13358},
year = {2026}
}