Domino Denoise: An Accurate Blind Zero-Shot Denoiser using Domino Tilings
This work addresses the challenge of accurate denoising without training datasets for image processing applications, though it is incremental as it builds on existing blind-spot network approaches.
The paper tackles the problem of blind zero-shot image denoising, where training data is unavailable, by proposing a hybrid method that combines a semi blind-spot network with a validation scheme using domino tilings to prevent overfitting. The result is an average PSNR increase of 0.28 and a threefold speed improvement over the state-of-the-art method Self2Self on synthetic Gaussian noise.
Because noise can interfere with downstream analysis, image denoising has come to occupy an important place in the image processing toolbox. The most accurate state-of-the-art denoisers typically train on a representative dataset. But gathering a training set is not always feasible, so interest has grown in blind zero-shot denoisers that train only on the image they are denoising. The most accurate blind-zero shot methods are blind-spot networks, which mask pixels and attempt to infer them from their surroundings. Other methods exist where all neurons participate in forward inference, however they are not as accurate and are susceptible to overfitting. Here we present a hybrid approach. We first introduce a semi blind-spot network where the network can see only a small percentage of inputs during gradient update. We then resolve overfitting by introducing a validation scheme where we split pixels into two groups and fill in pixel gaps using domino tilings. Our method achieves an average PSNR increase of $0.28$ and a three fold increase in speed over the current gold standard blind zero-shot denoiser Self2Self on synthetic Gaussian noise. We demonstrate the broader applicability of Pixel Domino Tiling by inserting it into a preciously published method.