Multi-illuminant Color Constancy via Multi-scale Illuminant Estimation and Fusion
This work improves color constancy for computer vision applications by handling local color casts more effectively, though it appears incremental as it builds on existing deep learning frameworks.
The paper tackled the problem of multi-illuminant color constancy by addressing the neglect of image scales in existing deep learning methods, proposing a multi-scale estimation and fusion approach that achieved state-of-the-art performance.
Multi-illuminant color constancy methods aim to eliminate local color casts within an image through pixel-wise illuminant estimation. Existing methods mainly employ deep learning to establish a direct mapping between an image and its illumination map, which neglects the impact of image scales. To alleviate this problem, we represent an illuminant map as the linear combination of components estimated from multi-scale images. Furthermore, we propose a tri-branch convolution networks to estimate multi-grained illuminant distribution maps from multi-scale images. These multi-grained illuminant maps are merged adaptively with an attentional illuminant fusion module. Through comprehensive experimental analysis and evaluation, the results demonstrate the effectiveness of our method, and it has achieved state-of-the-art performance.