Abstract
What will happen when unsupervised learning meets diffusion models for real-world image deraining? To answer it, we propose RainDiffusion, the first unsupervised image deraining paradigm based on diffusion models. Beyond the traditional unsupervised wisdom of image deraining, RainDiffusion introduces stable training of unpaired real-world data instead of weakly adversarial training. RainDiffusion consists of two cooperative branches: Non-diffusive Translation Branch (NTB) and Diffusive Translation Branch (DTB). NTB exploits a cycle-consistent architecture to bypass the difficulty in unpaired training of standard diffusion models by generating initial clean/rainy image pairs. DTB leverages two conditional diffusion modules to progressively refine the desired output with initial image pairs and diffusive generative prior, to obtain a better generalization ability of deraining and rain generation. Rain-Diffusion is a non adversarial training paradigm, serving as a new standard bar for real-world image deraining. Extensive experiments confirm the superiority of our RainDiffusion over un/semi-supervised methods and show its competitive advantages over fully-supervised ones.
Abstract (translated)
当 unsupervised learning 与扩散模型用于实际图像抑制时,会发生什么?为了回答这个问题,我们提出了 RainDiffusion,它是第一个基于扩散模型的 unsupervised 图像抑制范式。除了传统的图像抑制 unsupervised 智慧外, RainDiffusion 引入了稳定的配对真实数据的稳定训练,而不是弱对抗训练。 RainDiffusion 由两个合作分支组成:非扩散翻译分支(NTB)和扩散翻译分支(DTB)。 NTB利用循环一致性架构,通过生成初始清洁/雨水图像对,绕过标准扩散模型配对训练的难点。DTB利用两个条件扩散模块,逐步用初始图像对和扩散生成前向传播模型,逐渐优化期望输出,实现更好的抑制和雨生成泛化能力。 Rain-Diffusion 是一种无对抗训练范式,作为实际图像抑制的新标准。广泛的实验确认我们的 RainDiffusion 比无/半监督方法优越,并展示了它与完全监督方法的竞争优势。
URL
https://arxiv.org/abs/2301.09430