SVNR：具有去噪擴散的空間變異噪聲去除

摘要

最近，去噪擴散模型在生成任務中展現出令人印象深刻的成果。通過從龐大的訓練圖像集合中學習強大的先驗知識，這些模型能夠逐步將完全噪聲的影像進行一系列小的去噪步驟，轉變為清晰的自然影像，看似非常適合單張影像去噪。然而，有效地應用去噪擴散模型來消除現實噪聲比看起來更具挑戰性，因為它們的制定基於加性白色高斯噪聲，與現實世界影像中的噪聲不同。在這項研究中，我們提出了SVNR，一種新穎的去噪擴散形式，假設了更現實的、空間變異的噪聲模型。SVNR使得能夠將帶有噪聲的輸入影像作為去噪擴散過程的起點，同時也將其作為條件之一。為此，我們調整了擴散過程，使每個像素都能擁有自己的時間嵌入，並提出了支持空間變化時間映射的訓練和推斷方案。我們的形式化還考慮了存在於條件影像和沿著修改後的擴散過程的樣本之間的相關性。在我們的實驗中，我們展示了我們的方法相對於強大的擴散模型基線以及最先進的單張影像去噪方法的優勢。

English

Denoising diffusion models have recently shown impressive results in generative tasks. By learning powerful priors from huge collections of training images, such models are able to gradually modify complete noise to a clean natural image via a sequence of small denoising steps, seemingly making them well-suited for single image denoising. However, effectively applying denoising diffusion models to removal of realistic noise is more challenging than it may seem, since their formulation is based on additive white Gaussian noise, unlike noise in real-world images. In this work, we present SVNR, a novel formulation of denoising diffusion that assumes a more realistic, spatially-variant noise model. SVNR enables using the noisy input image as the starting point for the denoising diffusion process, in addition to conditioning the process on it. To this end, we adapt the diffusion process to allow each pixel to have its own time embedding, and propose training and inference schemes that support spatially-varying time maps. Our formulation also accounts for the correlation that exists between the condition image and the samples along the modified diffusion process. In our experiments we demonstrate the advantages of our approach over a strong diffusion model baseline, as well as over a state-of-the-art single image denoising method.

SVNR：具有去噪擴散的空間變異噪聲去除

SVNR: Spatially-variant Noise Removal with Denoising Diffusion

摘要

Support