vn-os/flip

A tool for visualizing and communicating the errors in rendered images.

ꟻLIP: A Tool for Visualizing and Communicating Errors in Rendered Images

By Pontus Andersson, Jim Nilsson, and Tomas Akenine-Möller, with Magnus Oskarsson, Kalle Åström, Mark D. Fairchild, and Peter Shirley.

This repository holds implementations of the LDR-ꟻLIP and HDR-ꟻLIP image error metrics. It also holds code for the ꟻLIP tool, to be presented in Ray Tracing Gems II.

A list of papers that use/cite ꟻLIP.

License

Copyright © 2020-2021, NVIDIA Corporation. All rights reserved.

This work is made available under the NVIDIA Source Code License.

For business inquiries, please contact [email protected].

For press and other inquiries, please contact Hector Marinez at [email protected].

Python (API and Tool)

Setup (with Anaconda3):

conda create -n flip python numpy matplotlib
conda activate flip
conda install -c conda-forge opencv
conda install -c conda-forge openexr-python

Usage:

Remember to activate the flip environment through conda activate flip before using the tool.

python flip.py --reference reference.{exr|png} --test test.{exr|png} [--options]

See the README in the python folder and run python flip.py -h for further information and usage instructions.

C++ and CUDA (API and Tool)

Setup:

The FLIP.sln solution contains one CUDA backend project and one pure C++ backend project.

Compiling the CUDA project requires a CUDA compatible GPU. Instruction on how to install CUDA can be found here.

Usage:

flip[-cuda].exe --reference reference.{exr|png} --test test.{exr|png} [options]

See the README in the cpp folder and run flip[-cuda].exe -h for further information and usage instructions.

PyTorch (Loss Function)

Setup (with Anaconda3):

conda create -n flip_dl python numpy matplotlib
conda activate flip_dl
conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge
conda install -c conda-forge openexr-python

Usage:

Remember to activate the flip_dl environment through conda activate flip_dl before using the loss function.

LDR- and HDR-ꟻLIP are implemented as loss modules in flip_loss.py. An example where the loss function is used to train a simple autoencoder is provided in train.py.

See the README in the pytorch folder for further information and usage instructions.

Citation

If your work uses the ꟻLIP tool to find the errors between low dynamic range images, please cite the LDR-ꟻLIP paper:
Paper | BibTeX

If it uses the ꟻLIP tool to find the errors between high dynamic range images, instead cite the HDR-ꟻLIP paper:
Paper | BibTeX

Should your work use the ꟻLIP tool in a more general fashion, please cite the Ray Tracing Gems II article:
Article (to be published in August 2021) | BibTeX