Two-stream CNN for gender classification and biometric identification using a dataset of 11K hand images.
Repositories
mahmoudnafifi repositories
Bias correction method for illuminant estimation -- JOSA 2019
Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)
[ICCV'25] CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy
PyTorch & Matlab code for the paper: CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks (TPAMI 2021).
A camera pipeline that allows accurate post-capture white balance editing (CIC best paper award, 2019)
Reference code for the paper: Deep White-Balance Editing (CVPR 2020). Our method is a deep learning multi-task framework for white-balance editing.
Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).
Download up to 4K images with specific keyword(s) from Flickr
Pytorch implementation of GridNet
Reference code for the paper HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms (CVPR 2021).
Image Recoloring Based on Object Color Distributions (Eurographics 2019)
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.
Matlab example of Multi-stream-CNN
Matlab implementation of Poisson image editing
Sensor-Independent Illumination Estimation for DNN Models (BMVC 2019)
Semantic information can help CNNs to get better illuminant estimation -- a proof of concept
WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
Python version of the WB augmenter (ICCV'19)