In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods. The network consists of one convolutional layer with max pooling, one fully connected layer and three output nodes. Within the network structure, feature learning and regression are integrated into one optimization process, which leads to a more effective model for estimating scene illumination. This approach achieves state-of-the-art performance on a standard dataset of RAW images. Preliminary experiments on images with spatially varying illumination demonstrate the stability of the local illuminant estimation ability of our CNN.

Bianco, S., Cusano, C., Schettini, R. (2015). Color constancy using CNNs. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015; Boston; United States; 7-12 June 2015 (pp.81-89). IEEE Computer Society [10.1109/CVPRW.2015.7301275].

Color constancy using CNNs

BIANCO, SIMONE
Primo
;
SCHETTINI, RAIMONDO
Ultimo
2015

Abstract

In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods. The network consists of one convolutional layer with max pooling, one fully connected layer and three output nodes. Within the network structure, feature learning and regression are integrated into one optimization process, which leads to a more effective model for estimating scene illumination. This approach achieves state-of-the-art performance on a standard dataset of RAW images. Preliminary experiments on images with spatially varying illumination demonstrate the stability of the local illuminant estimation ability of our CNN.
No
poster + paper
Estimation; Feature extraction; Image color analysis; Kernel; Lighting; Standards; Training; 1707; Electrical and Electronic Engineering
English
IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW - 7/12 June
9781467367592
http://ieeexplore.ieee.org/xpl/conferences.jsp
Bianco, S., Cusano, C., Schettini, R. (2015). Color constancy using CNNs. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015; Boston; United States; 7-12 June 2015 (pp.81-89). IEEE Computer Society [10.1109/CVPRW.2015.7301275].
Bianco, S; Cusano, C; Schettini, R
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/106770
Citazioni
  • Scopus 139
  • ???jsp.display-item.citation.isi??? 13
Social impact