提出一步扩散模型，高效还原模糊图像细节。
One-Step Diffusion Model for Image Motion-Deblurring
- 将扩散模型去噪过程简化为单步，提升推理速度。
- 在真实与合成数据集上均优于现有方法，保真度高。
- 适合需要快速、高质量去模糊的实时应用。
基于CNN和Transformer的单图去模糊方法虽表现良好，但存在感知局限、泛化能力差及对重度或复杂模糊处理困难等问题。尽管扩散模型可部分缓解上述问题，其多步去噪过程限制了实际应用。本文深入探索扩散模型在去模糊中的应用，提出一种一步扩散去模糊框架（OSDD），将去噪过程压缩至单步，显著提升推理效率并保持高保真度。为解决扩散模型中的保真度损失，引入增强型变分自编码器（eVAE）以改善结构恢复；构建高质量合成去模糊数据集以缓解感知崩溃，并设计动态双适配器（DDA）在保持保真度的同时提升感知质量。大量实验表明，该方法在全参考与无参考指标上均表现优异。代码与预训练模型将公开于 https://github.com/xyLiu339/OSDD。
原文摘要 · Abstract (English)
Currently, methods for single-image deblurring based on CNNs and transformers have demonstrated promising performance. However, these methods often suffer from perceptual limitations, poor generalization ability, and struggle with heavy or complex blur. While diffusion-based methods can partially address these shortcomings, their multi-step denoising process limits their practical usage. In this paper, we conduct an in-depth exploration of diffusion models in deblurring and propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step, significantly improving inference efficiency while maintaining high fidelity. To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration. Additionally, we construct a high-quality synthetic deblurring dataset to mitigate perceptual collapse and design a dynamic dual-adapter (DDA) to enhance perceptual quality while preserving fidelity. Extensive experiments demonstrate that our method achieves strong performance on both full and no-reference metrics. Our code and pre-trained model will be publicly available at https://github.com/xyLiu339/OSDD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。