papers AI Learner
The Github is limit! Click to go to the new site.

Conditional GANs for Multi-Illuminant Color Constancy: Revolution or Yet Another Approach?

2018-11-15
Oleksii Sidorov

Abstract

Non-uniform and multi-illuminant color constancy are important tasks, the solution of which will allow to discard information about lighting conditions in the image. Non-uniform illumination and shadows distort colors of real-world objects and mostly do not contain valuable information. Thus, many computer vision and image processing techniques would benefit from automatic discarding of this information at the pre-processing step. In this work we propose novel view on this classical problem via generative end-to-end algorithm, namely image conditioned Generative Adversarial Network. We also demonstrate the potential of the given approach for joint shadow detection and removal. Forced by the lack of training data, we render the largest existing shadow removal dataset and make it publicly available. It consists of approximately 6,000 pairs of wide field of view synthetic images with and without shadows.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.06604

PDF

https://arxiv.org/pdf/1811.06604


Similar Posts

Comments