Abstract
Image restoration has been an extensively researched topic in numerous fields. With the advent of deep learning, a lot of the current algorithms were replaced by algorithms that are more flexible and robust. Deep networks have demonstrated impressive performance in a variety of tasks like blind denoising, image enhancement, deblurring, super-resolution, inpainting, among others. Most of these learning-based algorithms use a large amount of clean data during the training process. However, in certain applications in medical image processing, one may not have access to a large amount of clean data. In this paper, we propose a method for denoising that attempts to learn the denoising process by pushing the noisy data close to the clean data manifold, using only noisy images during training. Furthermore, we use perceptual loss terms and an iterative refinement step to further refine the clean images without losing important features.
Abstract (translated)
图像恢复一直是众多领域研究的热点。随着深度学习的出现,许多现有的算法被更灵活、更健壮的算法所取代。深层网络在各种任务中表现出了令人印象深刻的性能,如盲去噪、图像增强、去模糊、超分辨率、修复等。大多数基于学习的算法在训练过程中使用大量干净的数据。然而,在医学图像处理的某些应用中,人们可能无法获得大量干净的数据。本文提出了一种去噪方法,通过将噪声数据推近干净的数据流形,在训练过程中只使用噪声图像来学习去噪过程。此外,我们使用知觉损失项和迭代细化步骤进一步细化干净的图像,而不丢失重要的特征。
URL
https://arxiv.org/abs/1904.12323