Superpixel-based Color Transfer - Archive ouverte HAL Access content directly
Conference Papers Year :

Superpixel-based Color Transfer

Abstract

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.
Fichier principal
Vignette du fichier
Giraud_SCT_ICIP17.pdf (4.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01519644 , version 2 (13-03-2019)

Identifiers

  • HAL Id : hal-01519644 , version 2

Cite

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. Superpixel-based Color Transfer. IEEE International Conference on Image Processing (ICIP'17), Sep 2017, Beijing, China. pp.700-704. ⟨hal-01519644⟩

Collections

CNRS ANR
291 View
1130 Download

Share

Gmail Facebook Twitter LinkedIn More