# Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance

## TL;DR

This paper introduces a perceptual regulariser based on the Normalised Laplacian Pyramid Distance (NLPD) for training cGANs, which enhances the realism and quality of generated images by aligning them more closely with human perception.

## Contribution

It proposes using NLPD as a novel perceptual regulariser in cGAN training, improving image realism and segmentation accuracy over traditional L1 distance.

## Key findings

- NLPD regularisation yields more realistic contrast in generated images.
- Using NLPD improves image segmentation accuracy.
- NLPD enhances no-reference image quality metrics.

## Abstract

In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an alternative perceptual regulariser for image-to-image translation using conditional generative adversarial networks (cGANs). To do so automatically (avoiding visual inspection), we use the Normalised Laplacian Pyramid Distance (NLPD) to measure the perceptual similarity between the generated image and the original image. The NLPD is based on the principle of normalising the value of coefficients with respect to a local estimate of mean energy at different scales and has already been successfully tested in different experiments involving human perception. We compare this regulariser with the originally proposed L1 distance and note that when using NLPD the generated images contain more realistic values for both local and global contrast. We found that using NLPD as a regulariser improves image segmentation accuracy on generated images as well as improving two no-reference image quality metrics.