PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance

10/28/2019
by   Alexander Hepburn, et al.
0

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system. To address this, we present PerceptNet, a convolutional neural network where the architecture has been chosen to reflect the structure and various stages in the human visual system. We evaluate PerceptNet on various traditional perception datasets and note strong performance on a number of them as compared with traditional image quality metrics. We also show that including a nonlinearity inspired by the human visual system in classical deep neural networks architectures can increase their ability to judge perceptual similarity.

READ FULL TEXT

page 3

page 4

research
02/17/2022

A study of deep perceptual metrics for image quality assessment

Several metrics exist to quantify the similarity between images, but the...
research
02/25/2022

Deep Neural Network for Automatic Assessment of Dysphonia

The purpose of this work is to contribute to the understanding and impro...
research
10/06/2017

Eigen-Distortions of Hierarchical Representations

We develop a method for comparing hierarchical image representations in ...
research
08/16/2020

Visual stream connectivity predicts assessments of image quality

Some biological mechanisms of early vision are comparatively well unders...
research
08/14/2023

Robustified ANNs Reveal Wormholes Between Human Category Percepts

The visual object category reports of artificial neural networks (ANNs) ...
research
10/24/2021

Quality Map Fusion for Adversarial Learning

Generative adversarial models that capture salient low-level features wh...
research
02/26/2023

Analysis of Deep Image Quality Models

Subjective image quality measures based on deep neural networks are very...

Please sign up or login with your details

Forgot password? Click here to reset