Journal
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 3613-3622Publisher
IEEE
DOI: 10.1109/CVPR42600.2020.00367
Keywords
-
Categories
Funding
- National Natural Science Foundation of China [61902253]
Ask authors/readers for more resources
Previous deep learning approaches to color constancy usually directly estimate illuminant value from input image. Such approaches might suffer heavily from being sensitive to the variation of image content. To overcome this problem, we introduce a deep metric learning approach named Illuminant-Guided Triplet Network (IGTN) to color constancy. IGTN generates an Illuminant Consistent and Discriminative Feature (ICDF) for achieving robust and accurate illuminant color estimation. ICDF is composed of semantic and color features based on a learnable color histogram scheme. In the ICDF space, regardless of the similarities of their contents, images taken under the same or similar illuminants are placed close to each other and at the same time images taken under different illuminants are placed far apart. We also adopt an endto-end training strategy to simultaneously group image features and estimate illuminant value, and thus our approach does not have to classify illuminant in a separate module. We evaluate our method on two public datasets and demonstrate our method outperforms state-of-the-art approaches. Furthermore, we demonstrate that our method is less sensitive to image appearances, and can achieve more robust and consistent results than other methods on a High Dynamic Range dataset.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available