Superpixel-based Color Transfer

03/14/2019
by   Remi Giraud, et al.
0

In this work, we propose a fast superpixel-based color transfer method (SCT) between two images. Superpixels enable to decrease the image dimension and to extract a reduced set of color candidates. We propose to use a fast approximate nearest neighbor matching algorithm in which we enforce the match diversity by limiting the selection of the same superpixels. A fusion framework is designed to transfer the matched colors, and we demonstrate the improvement obtained over exact matching results. Finally, we show that SCT is visually competitive compared to state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/04/2016

Recoding Color Transfer as a Color Homography

Color transfer is an image editing process that adjusts the colors of a ...
research
10/23/2019

Stain Style Transfer using Transitive Adversarial Networks

Digitized pathological diagnosis has been in increasing demand recently....
research
08/08/2022

CLIP-based Neural Neighbor Style Transfer for 3D Assets

We present a method for transferring the style from a set of images to a...
research
05/30/2022

Adaptive color transfer from images to terrain visualizations

Terrain mapping is not only dedicated to communicating how high or how s...
research
10/02/2017

Neural Color Transfer between Images

We propose a new algorithm for color transfer between images that have p...
research
01/22/2017

Multimodal Fusion via a Series of Transfers for Noise Removal

Near-infrared imaging has been considered as a solution to provide high ...
research
04/10/2014

Real-time Decolorization using Dominant Colors

Decolorization is the process to convert a color image or video to its g...

Please sign up or login with your details

Forgot password? Click here to reset