DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

05/06/2020
by   Mor Avi-Aharon, et al.
0

We present the DeepHist - a novel Deep Learning framework for augmenting a network by histogram layers and demonstrate its strength by addressing image-to-image translation problems. Specifically, given an input image and a reference color distribution we aim to generate an output image with the structural appearance (content) of the input (source) yet with the colors of the reference. The key idea is a new technique for a differentiable construction of joint and color histograms of the output images. We further define a color distribution loss based on the Earth Mover's Distance between the output's and the reference's color histograms and a Mutual Information loss based on the joint histograms of the source and the output images. Promising results are shown for the tasks of color transfer, image colorization and edges → photo, where the color distribution of the output image is controlled. Comparison to Pix2Pix and CyclyGANs are shown.

READ FULL TEXT

page 2

page 7

page 8

page 13

page 14

page 15

page 16

page 18

research
12/12/2019

Hue-Net: Intensity-based Image-to-Image Translation with Differentiable Histogram Loss Functions

We present the Hue-Net - a novel Deep Learning framework for Intensity-b...
research
06/24/2020

GIFnets: Differentiable GIF Encoding Framework

Graphics Interchange Format (GIF) is a widely used image file format. Du...
research
04/03/2018

A Modified Image Comparison Algorithm Using Histogram Features

This article discuss the problem of color image content comparison. Part...
research
09/29/2021

USIS: Unsupervised Semantic Image Synthesis

Semantic Image Synthesis (SIS) is a subclass of image-to-image translati...
research
05/08/2023

Domain Agnostic Image-to-image Translation using Low-Resolution Conditioning

Generally, image-to-image translation (i2i) methods aim at learning mapp...
research
08/19/2020

Slide-free MUSE Microscopy to H E Histology Modality Conversion via Unpaired Image-to-Image Translation GAN Models

MUSE is a novel slide-free imaging technique for histological examinatio...
research
12/07/2018

Color Constancy by GANs: An Experimental Survey

In this paper, we formulate the color constancy task as an image-to-imag...

Please sign up or login with your details

Forgot password? Click here to reset