Proceedings ArticleDOI
When Color Constancy Goes Wrong: Correcting Improperly White-Balanced Images
Mahmoud Afifi,Brian Price,Scott Cohen,Michael S. Brown +3 more
- pp 1535-1544
Reads0
Chats0
TLDR
This paper introduces a k-nearest neighbor strategy that is able to compute a nonlinear color mapping function to correct the image's colors and shows the method is highly effective and generalizes well to camera models not in the training set.Abstract:
This paper focuses on correcting a camera image that has been improperly white-balanced. This situation occurs when a camera's auto white balance fails or when the wrong manual white-balance setting is used. Even after decades of computational color constancy research, there are no effective solutions to this problem. The challenge lies not in identifying what the correct white balance should have been, but in the fact that the in-camera white-balance procedure is followed by several camera-specific nonlinear color manipulations that make it challenging to correct the image's colors in post-processing. This paper introduces the first method to explicitly address this problem. Our method is enabled by a dataset of over 65,000 pairs of incorrectly white-balanced images and their corresponding correctly white-balanced images. Using this dataset, we introduce a k-nearest neighbor strategy that is able to compute a nonlinear color mapping function to correct the image's colors. We show our method is highly effective and generalizes well to camera models not in the training set.read more
Citations
More filters
Book
Color Appearance Models
TL;DR: This book is a good overview of the most important and relevant literature regarding color appearance models and offers insight into the preferred solutions.
Proceedings ArticleDOI
Deep White-Balance Editing
Mahmoud Afifi,Michael S. Brown +1 more
TL;DR: A deep neural network (DNN) architecture trained in an end-to-end manner to learn the correct white balance for sRGB images that are rendered with the incorrect white balance is introduced.
Proceedings ArticleDOI
What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance
Mahmoud Afifi,Michael S. Brown +1 more
TL;DR: In this paper, the authors explore how strong color casts caused by incorrectly applied computational color constancy - referred to as white balance (WB) in photography - negatively impact the performance of DNNs targeting image segmentation and classification.
Posted Content
Learning Multi-Scale Photo Exposure Correction
TL;DR: This work proposes a coarse- to-fine deep neural network model, trainable in an end-to-end manner, that addresses each sub-problem separately of the exposure correction problem as two main sub-problems: color enhancement and detail enhancement.
Proceedings Article
Sensor-Independent Illumination Estimation for DNN Models.
Mahmoud Afifi,Michael S. Brown +1 more
TL;DR: This paper learns a sensor-independent working space that can be used to canonicalize the RGB values of any arbitrary camera sensor and allows unseen camera sensors to be used on a single DNN model trained on this working space.
References
More filters
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Journal ArticleDOI
Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning
TL;DR: Experiments show that SCG is considerably faster than BP, CGL, and BFGS, and avoids a time consuming line search.
Proceedings ArticleDOI
Recovering high dynamic range radiance maps from photographs
Paul Debevec,Jitendra Malik +1 more
TL;DR: This work discusses how this work is applicable in many areas of computer graphics involving digitized photographs, including image-based modeling, image compositing, and image processing, and demonstrates a few applications of having high dynamic range radiance maps.
Journal ArticleDOI
A spatial processor model for object colour perception
TL;DR: In this article, a comprehensive mathematical model to account for colour constancy is formulated, where the visual system is able to measure true object colour in complex scenes under a broad range of spectral compositions, for the illumination; it is assumed that the visual systems must implicitly estimate and illuminant.
Proceedings ArticleDOI
Three things everyone should know to improve object retrieval
TL;DR: A new method to compare SIFT descriptors (RootSIFT) which yields superior performance without increasing processing or storage requirements, and a novel method for query expansion where a richer model for the query is learnt discriminatively in a form suited to immediate retrieval through efficient use of the inverted index.