Flash Lightens Gray Pixels
This work addresses a specific problem in computer vision for applications like image processing, but it is incremental as it builds on existing gray pixel detection methods.
The paper tackled the problem of spatial illumination estimation in scenes with multiple illuminants by using flash photography to detect gray pixels, resulting in significant performance improvement without requiring illuminant prior, training data, or flash calibration.
In the real world, a scene is usually cast by multiple illuminants and herein we address the problem of spatial illumination estimation. Our solution is based on detecting gray pixels with the help of flash photography. We show that flash photography significantly improves the performance of gray pixel detection without illuminant prior, training data or calibration of the flash. We also introduce a novel flash photography dataset generated from the MIT intrinsic dataset.