burst-denoising

by google

214 Stars 46 Forks Last release: Not found Apache License 2.0 2 Commits 0 Releases

Available items

No Items, yet!

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:

Burst Denoising with Kernel Prediction Networks

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.

Dependencies

This code uses the following external packages:

  • TensorFlow
  • NumPy
  • SciPy
  • Matplotlib

Dataset

Synthetic training data is generated using the OpenImages dataset, which can be manually downloaded following these instructions.

Training

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

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.