Low-Light Image Restoration Based on Retina Model using Neural Networks
This work addresses low-light image restoration for computer vision applications, but it is incremental as it builds on existing neural network approaches with a bio-inspired twist.
The authors tackled low-light image restoration by proposing a simple neural network inspired by the retina model, which reduces computational overhead compared to traditional methods and achieves results comparable to complex deep learning models from a subjective perceptual perspective.
We report the possibility of using a simple neural network for effortless restoration of low-light images inspired by the retina model, which mimics the neurophysiological principles and dynamics of various types of optical neurons. The proposed neural network model saves the cost of computational overhead in contrast with traditional signal-processing models, and generates results comparable with complicated deep learning models from the subjective perceptual perspective. This work shows that to directly simulate the functionalities of retinal neurons using neural networks not only avoids the manually seeking for the optimal parameters, but also paves the way to build corresponding artificial versions for certain neurobiological organizations.