ﻻ يوجد ملخص باللغة العربية
It has been demonstrated many times that the behavior of the human visual system is connected to the statistics of natural images. Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function. In this paper, we aim to unravel the non-trivial relationship between the probability distribution of the data, perceptual distances, and unsupervised machine learning. To this end, we show that perceptual sensitivity is correlated with the probability of an image in its close neighborhood. We also explore the relation between distances induced by autoencoders and the probability distribution of the data used for training them, as well as how these induced distances are correlated with human perception. Finally, we discuss why perceptual distances might not lead to noticeable gains in performance over standard Euclidean distances in common image processing tasks except when data is scarce and the perceptual distance provides regularization.
We introduce a learning strategy for contrast-invariant image registration without requiring imaging data. While classical registration methods accurately estimate the spatial correspondence between images, they solve a costly optimization problem fo
In this paper, we propose an image quality transformer (IQT) that successfully applies a transformer architecture to a perceptual full-reference image quality assessment (IQA) task. Perceptual representation becomes more important in image quality as
We analyze the spaces of images encoded by generative networks of the BigGAN architecture. We find that generic multiplicative perturbations away from the photo-realistic point often lead to images which appear as artistic renditions of the correspon
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
Identification of a person from fingerprints of good quality has been used by commercial applications and law enforcement agencies for many years, however identification of a person from latent fingerprints is very difficult and challenging. A latent