color-constancy

Reference code for the paper: Deep White-Balance Editing (CVPR 2020). Our method is a deep learning multi-task framework for white-balance editing.

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

Reference code for the paper Auto White-Balance Correction for Mixed-Illuminant Scenes.

[CVPR2020] A Multi-Hypothesis Approach to Color Constancy

An official TensorFlow implementation of “CLCC: Contrastive Learning for Color Constancy” accepted at CVPR 2021.

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.

A PyTorch implementation of FC4: Fully Convolutional Color Constancy with Confidence-weighted Pooling

Implementation of the method described in the paper "Quasi-unsupervised color constancy" - CVPR 2019

Code for "Time-Aware Auto White Balance in Mobile Photography"

Code for "Time-Aware Auto White Balance in Mobile Photography" (ICCV 2025)

Companion repository for the paper "Evaluating the Faithfulness of Causality in Saliency-Based Explanations of Deep Learning Models for Temporal Colour Constancy" submitted to XAI2024.

Companion repository for the paper "Cascading Convolutional Temporal Color Constancy" submitted to the Journal of Electronic Imaging

A Convolutional Framework for Color Constancy [IEEE TNNLS 2024]

A Python implementation of color constancy algorithms for photo enhancement, based on the comprehensive review by Foster (2011). This package implements several key color constancy techniques including Gray World assumption, White Patch correction, Von Kries adaptation, Retinex enhancement, and spatial color correction methods.

Not a serious implementation of Deep white balance in Tensorflow. Aimed for personal learning.