A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina
This work addresses image denoising, particularly for non-Gaussian noise, with potential applications in computer vision, though it appears incremental as it builds on existing neural network methods.
The authors tackled blind image denoising by introducing the PR-filter, a simple filter inspired by electrically coupled photoreceptors, which achieved outstanding SSIM performance on the BSD68 dataset and enhanced state-of-the-art convolutional neural networks for non-Gaussian noise.
Photoreceptors in the retina are coupled by electrical synapses called "gap junctions". It has long been established that gap junctions increase the signal-to-noise ratio of photoreceptors. Inspired by electrically coupled photoreceptors, we introduced a simple filter, the PR-filter, with only one variable. On BSD68 dataset, PR-filter showed outstanding performance in SSIM during blind denoising tasks. It also significantly improved the performance of state-of-the-art convolutional neural network blind denosing on non-Gaussian noise. The performance of keeping more details might be attributed to small receptive field of the photoreceptors.