Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
By Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, Jian-zhuo Liu. Computer Vision and Pattern Recognition, 2021
464 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/dba9d633e0be0500ea1d5c6d1bd60f281061c1f1
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Media Technology
Citations in the corpus
- Learning a Simple Low-Light Image Enhancer from Paired Low-Light Instances (2023, background): “For example, one can use neighbor masks [10] to generate two similar low-light images from a degraded observation.”
- A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends (2023, background): “…distillation [188], optical flow prediction [189], vision-language navigation [190], physiological signal estimation [191], [192], image denoising [193], [194], object detection [195], [196], [197], super-resolution [198], [199], voxel prediction from 2D images [200], and ego-motion [201], [202].”
- Uformer: A General U-Shaped Transformer for Image Restoration (2021, background): “Actually, neighboring pixels are crucial references for image restoration [6, 21].”