一步殘差遷移擴散：基於蒸餾的圖像超分辨率方法

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）的擴散模型能夠生成高質量的視覺效果，但需要昂貴的計算成本。儘管已經開發了多種方法來加速基於擴散的SR模型，但一些方法（例如SinSR）未能產生逼真的感知細節，而其他方法（例如OSEDiff）可能會虛構不存在的結構。為了解決這些問題，我們提出了RSD，這是一種新的蒸餾方法，適用於ResShift，這是頂級的基於擴散的SR模型之一。我們的方法基於訓練學生網絡生成這樣的圖像，使得在這些圖像上訓練的新假ResShift模型將與教師模型一致。RSD實現了單步恢復，並且大幅超越了教師模型。我們展示了我們的蒸餾方法可以超越其他基於ResShift的蒸餾方法——SinSR，使其與最先進的基於擴散的SR蒸餾方法相媲美。與基於預訓練文本到圖像模型的SR方法相比，RSD產生了具有競爭力的感知質量，提供了與退化輸入圖像更好對齊的圖像，並且需要更少的參數和GPU內存。我們在各種真實世界和合成數據集上提供了實驗結果，包括RealSR、RealSet65、DRealSR、ImageNet和DIV2K。

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.