An approach to image denoising using manifold approximation without clean images
This addresses a practical limitation in fields like medical imaging where clean data is scarce, though it is an incremental improvement over existing unsupervised denoising methods.
The paper tackles the problem of image denoising without access to clean training data, proposing a method that learns by approximating the clean data manifold using only noisy images, and achieves competitive results on standard benchmarks.
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.