Bag of Color Features For Color Constancy

06/11/2019
by   Firas Laakom, et al.
4

In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces the number of parameters needed for illumination estimation. At the same time, the proposed method is consistent with the color constancy assumption stating that global spatial information is not relevant for illumination estimation and local information ( edges, etc.) is sufficient. Furthermore, BoCF is consistent with color constancy statistical approaches and can be interpreted as a learning-based generalization of many statistical approaches. To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention. BoCF approach and its variants achieve competitive, compared to the state of the art, results while requiring much fewer parameters on three benchmark datasets: ColorChecker RECommended, INTEL-TUT version 2, and NUS8.

READ FULL TEXT

page 1

page 5

page 6

page 9

research
08/29/2016

Approaching the Computational Color Constancy as a Classification Problem through Deep Learning

Computational color constancy refers to the problem of computing the ill...
research
11/17/2019

Dense Color Constancy with Effective Edge Augmentation

Recently, computational color constancy via convolutional neural network...
research
10/01/2013

Using the Random Sprays Retinex Algorithm for Global Illumination Estimation

In this paper the use of Random Sprays Retinex (RSR) algorithm for globa...
research
05/06/2020

Probabilistic Color Constancy

In this paper, we propose a novel unsupervised color constancy method, c...
research
10/23/2019

INTEL-TAU: A Color Constancy Dataset

In this paper, we describe a new large dataset for illumination estimati...
research
06/25/2018

PILOT: A Pixel Intensity Driven Illuminant Color Estimation Framework for Color Constancy

In this study, a CNN based Pixel Intensity driven iLluminant cOlor esTim...
research
06/04/2019

Color Constancy Convolutional Autoencoder

In this paper, we study the importance of pre-training for the generaliz...

Please sign up or login with your details

Forgot password? Click here to reset