flâneur

Neighbor2Neighbor

arxiv.org · 6,917 words · saved by 1 readers

In the last few years, image denoising has benefited a lot from the fast development of neural networks. However, the requirement of large amounts of noisy-clean image pairs for supervision limits the wide use of these models. Although there have been a few attempts in training an image denoising model with only single noisy images, existing self-supervised denoising approaches suffer from inefficient network training, loss of useful information, or dependence on noise modeling. In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images. Firstly, a random neighbor sub-sampler is proposed for the generation of training image pairs. In detail, input and target used to train a network are images sub-sampled from the same noisy image, satisfying the requirement that paired pixels of paired images are neighbors and have very similar appearance with each other. Secondly, a denoising network is trained on sub-sampled training pairs generated in the first stage, with a proposed regularizer as additional loss for better performance. The proposed Neighbor2Neighbor framework is able to enjoy the progress of state-of-the-art supervised denoising networks in network architecture design. Moreover, it avoids heavy dependence on the assumption of the noise distribution. We explain our approach from a theoretical perspective and further validate it through extensive experiments, including synthetic experiments with different noise distributions in sRGB space and real-world experiments on a denoising benchmark dataset in raw-RGB space.

Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images Tao Huang1,2 *, Songjiang Li2 , Xu Jia2,3†, Huchuan Lu3 , Jianzhuang Liu2 1 Renmin University of China, 2 Noah’s Ark Lab, Huawei Technologies, 3 Dalian University of Technology tao.huang2018@ruc.edu.cn jiayushenyang@gmail.com…

saved by

related reading