Convolutional Color Constancy

Abstract

Color constancy is the problem of inferring the color of the light that illuminated a scene, usually so that the illumination color can be removed. Because this problem is underconstrained, it is often solved by modeling the statistical regularities of the colors of natural objects and illumination. In contrast, in this paper we reformulate the problem of color constancy as a 2D spatial localization task in a log-chrominance space, thereby allowing us to apply techniques from object detection and structured prediction to the color constancy problem. By directly learning how to discriminate between correctly white-balanced images and poorly white-balanced images, our model is able to improve performance on standard benchmarks by nearly 40%.

References in corpus (1)

• ADADELTA: An Adaptive Learning Rate Method

Cited by in corpus (7)

• Deep Structured-Output Regression Learning for Computational Color Constancy
• Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
• Colour Constancy: Biologically-inspired Contrast Variant Pooling Mechanism
• CroP: Color Constancy Benchmark Dataset Generator
• Cascading Convolutional Color Constancy
• Fast Color Constancy with Patch-wise Bright Pixels
• Illumination Estimation Challenge: experience of past two years