/kpcn

PyTorch implementation of Kernel-predicting convolutional networks for denoising Monte Carlo renderings (Jupyter notebook)

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

KPCN

PyTorch implementation of Kernel-predicting convolutional networks paper in form of Jupyter notebook.

The idea is to apply convolutional networks to denoise Monte Carlo renderings.

This was done as a part of my MSc term project at Faculty of Electrical Engineering and Computing (FER), University of Zagreb, Croatia.