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. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/CVPRW.2015.7301275 | 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |
Keywords | Field | DocType |
color constancy,convolutional neural network,image patches,hand-crafted features,max pooling,network structure,feature learning,regression analysis,optimization process,RAW images,local illuminant estimation ability,CNN | Kernel (linear algebra),Color constancy,Computer vision,Pattern recognition,Regression,Convolutional neural network,Computer science,Pooling,Feature extraction,Artificial intelligence,Standard illuminant,Feature learning | Journal |
Volume | Issue | ISSN |
abs/1504.04548 | 1 | 2160-7508 |
Citations | PageRank | References |
32 | 0.95 | 26 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Bianco | 1 | 226 | 24.48 |
Cusano, C. | 2 | 114 | 5.11 |
Raimondo Schettini | 3 | 1476 | 154.06 |