Extending Stein's unbiased risk estimator to train deep denoisers with correlated pairs of noisy images
This addresses the challenge of unsupervised denoising for applications where collecting clean data is difficult, offering an incremental improvement over existing methods.
The paper tackled the problem of training deep denoisers without clean ground truth by extending Stein's unbiased risk estimator (SURE) to use correlated pairs of noisy images, achieving better performance than SURE and comparable results to Noise2Noise, and outperforming both in cases with imperfect ground truth.
Recently, Stein's unbiased risk estimator (SURE) has been applied to unsupervised training of deep neural network Gaussian denoisers that outperformed classical non-deep learning based denoisers and yielded comparable performance to those trained with ground truth. While SURE requires only one noise realization per image for training, it does not take advantage of having multiple noise realizations per image when they are available (e.g., two uncorrelated noise realizations per image for Noise2Noise). Here, we propose an extended SURE (eSURE) to train deep denoisers with correlated pairs of noise realizations per image and applied it to the case with two uncorrelated realizations per image to achieve better performance than SURE based method and comparable results to Noise2Noise. Then, we further investigated the case with imperfect ground truth (i.e., mild noise in ground truth) that may be obtained considering painstaking, time-consuming, and even expensive processes of collecting ground truth images with multiple noisy images. For the case of generating noisy training data by adding synthetic noise to imperfect ground truth to yield correlated pairs of images, our proposed eSURE based training method outperformed conventional SURE based method as well as Noise2Noise.