WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
-
Updated
Sep 20, 2024 - MATLAB
WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
C++ Automated white balance using lodepng and some color correction
Reference code for the paper Interactive White Balancing for Camera-Rendered Images Mahmoud Afifi and Michael S. Brown. In Color and Imaging Conference (CIC), 2020.
A suite of tests to assess attention faithfulness for explainability
Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)
Reference code for the paper: Deep White-Balance Editing (CVPR 2020). Our method is a deep learning multi-task framework for white-balance editing.
Sensor-Independent Illumination Estimation for DNN Models (BMVC 2019)
Official codes for 'Domain Adversarial Learning for Color Constancy'
Reference code for the paper Auto White-Balance Correction for Mixed-Illuminant Scenes.
Semantic information can help CNNs to get better illuminant estimation -- a proof of concept
White balance camera-rendered sRGB images (CVPR 2019) [Matlab & Python]
Implementation of the method described in the paper "Quasi-unsupervised color constancy" - CVPR 2019
Code for "Truncated Edge-based Color Constancy"
Source code and dataset for the paper titled "Colour alignment for relative colour constancy via non-standard references"
Not a serious implementation of Deep white balance in Tensorflow. Aimed for personal learning.
An official TensorFlow implementation of “CLCC: Contrastive Learning for Color Constancy” accepted at CVPR 2021.
[CVPR2020] A Multi-Hypothesis Approach to Color Constancy
Bias correction method for illuminant estimation -- JOSA 2019
Cube++ is a novel dataset collected for illumination estimation problem. It has 4890 raw 18-megapixel images, each containing a SpyderCube color target in their scenes, manually labelled categories, and ground truth illumination chromaticities.
Fully supervised binary classification of skin lesions from dermatoscopic images using an ensemble of diverse CNN architectures (EfficientNet-B6, Inception-V3, SEResNeXt-101, SENet-154, DenseNet-169) with multi-scale input.
Add a description, image, and links to the color-constancy topic page so that developers can more easily learn about it.
To associate your repository with the color-constancy topic, visit your repo's landing page and select "manage topics."