Generating Images with Perceptual Similarity Metrics based on Deep Networks

02/08/2016
by   Alexey Dosovitskiy, et al.
0

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual similarity metrics (DeePSiM), that mitigate this problem. Instead of computing distances in the image space, we compute distances between image features extracted by deep neural networks. This metric better reflects perceptually similarity of images and thus leads to better results. We show three applications: autoencoder training, a modification of a variational autoencoder, and inversion of deep convolutional networks. In all cases, the generated images look sharp and resemble natural images.

READ FULL TEXT

page 5

page 6

page 7

page 8

page 10

page 11

page 12

page 13

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
03/16/2020

Pretraining Image Encoders without Reconstruction via Feature Prediction Loss

This work investigates three different loss functions for autoencoder-ba...
research
07/27/2023

R-LPIPS: An Adversarially Robust Perceptual Similarity Metric

Similarity metrics have played a significant role in computer vision to ...
research
06/08/2021

On the relation between statistical learning and perceptual distances

It has been demonstrated many times that the behavior of the human visua...
research
06/10/2019

E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles

It has been recently shown that the hidden variables of convolutional ne...
research
07/06/2022

Identifying and Mitigating Flaws of Deep Perceptual Similarity Metrics

Measuring the similarity of images is a fundamental problem to computer ...
research
04/05/2023

Deep Perceptual Similarity is Adaptable to Ambiguous Contexts

The concept of image similarity is ambiguous, meaning that images that a...

Please sign up or login with your details

Forgot password? Click here to reset