The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
Ben Mildenhall | Jonathan T. Barron | Jiawen Chen | Dillon Sharlet | Ren Ng | Robert Carroll
This is not an official Google product. This repository contains code for training models from the paper Burst Denoising with Kernel Prediction Networks.
This code uses the following external packages:
Synthetic training data is generated using the OpenImages dataset, which can be manually downloaded following these instructions.
Run the following command to train the kernel prediction network (KPN) burst denoising model:
python kpn_train.py --dataset_dir $OPEN_IMAGES_DATASET_DIR --data_dir $REAL_BURST_DATA_DIR