TransCC: Transformer-based Multiple Illuminant Color Constancy Using Multitask Learning

by   Shuwei Li, et al.

Multi-illuminant color constancy is a challenging problem with only a few existing methods. For example, one prior work used a small set of predefined white balance settings and spatially blended among them, limiting the solution to predefined illuminations. Another method proposed a generative adversarial network and an angular loss, yet the performance is suboptimal due to the lack of regularization for multi-illumination colors. This paper introduces a transformer-based multi-task learning method to estimate single and multiple light colors from a single input image. To help our deep learning model have better cues of the light colors, achromatic-pixel detection, and edge detection are used as auxiliary tasks in our multi-task learning setting. By exploiting extracted content features from the input image as tokens, illuminant color correlations between pixels are learned by leveraging contextual information in our transformer. Our transformer approach is further assisted via a contrastive loss defined between the input, output, and ground truth. We demonstrate that our proposed model achieves 40.7 multi-illuminant color constancy method on a multi-illuminant dataset (LSMI). Moreover, our model maintains a robust performance on the single illuminant dataset (NUS-8) and provides 22.3 color constancy method.


page 1

page 3

page 4

page 6

page 8


Multi-color balance for color constancy

In this paper, we propose a novel multi-color balance adjustment for col...

Spatially varying white balancing for mixed and non-uniform illuminants

In this paper, we propose a novel white balance adjustment, called "spat...

Multi-color balancing for correctly adjusting the intensity of target colors

In this paper, we propose a novel multi-color balance method for reducin...

Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis

Recently, deep learning-based generative models have been introduced to ...

CORE: Color Regression for Multiple Colors Fashion Garments

Among all fashion attributes, color is challenging to detect due to its ...

Multiple Hypothesis Colorization

In this work we focus on the problem of colorization for image compressi...

Transformer-based Multi-task Learning for Disaster Tweet Categorisation

Social media has enabled people to circulate information in a timely fas...

Please sign up or login with your details

Forgot password? Click here to reset