将模糊形成过程融入扩散模型，实现更自然的图像去模糊。
BlurDM: A Blur Diffusion Model for Image Deblurring
- 用双扩散前向过程隐式建模运动模糊，模拟连续曝光效果。
- 在反向生成中同时去噪与去模糊，输入纯高斯噪声即可恢复清晰图像。
- 在潜在空间运行，可灵活嵌入各类去模糊网络，提升性能。
扩散模型在动态场景去模糊方面展现出潜力；然而，现有研究常未能充分利用模糊过程的内在特性，限制了其潜力。为此，我们提出一种模糊扩散模型（BlurDM），将模糊生成过程无缝融入扩散框架以实现图像去模糊。观察到运动模糊源于连续曝光，BlurDM通过双扩散前向方案，同时将噪声和模糊扩散到清晰图像上。在反向生成过程中，我们推导出双去噪与去模糊公式，仅需以模糊图像为条件、输入纯高斯噪声，即可恢复清晰图像。此外，为高效集成至去模糊网络，我们在潜在空间中执行BlurDM，构建一个灵活的先验生成网络。大量实验表明，BlurDM在四个基准数据集上显著且一致地提升了现有去模糊方法的性能。
原文摘要 · Abstract (English)
Diffusion models show promise for dynamic scene deblurring; however, existing studies often fail to leverage the intrinsic nature of the blurring process within diffusion models, limiting their full potential. To address it, we present a Blur Diffusion Model (BlurDM), which seamlessly integrates the blur formation process into diffusion for image deblurring. Observing that motion blur stems from continuous exposure, BlurDM implicitly models the blur formation process through a dual-diffusion forward scheme, diffusing both noise and blur onto a sharp image. During the reverse generation process, we derive a dual denoising and deblurring formulation, enabling BlurDM to recover the sharp image by simultaneously denoising and deblurring, given pure Gaussian noise conditioned on the blurred image as input. Additionally, to efficiently integrate BlurDM into deblurring networks, we perform BlurDM in the latent space, forming a flexible prior generation network for deblurring. Extensive experiments demonstrate that BlurDM significantly and consistently enhances existing deblurring methods on four benchmark datasets. The project page is available at https://jin-ting-he.github.io/BlurDM/.
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。