Home

Awesome

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing

Quick start

conda env create -f environment.yml
conda activate PhySG
cd code
python training/exp_runner.py --conf confs_sg/default.conf \
                              --data_split_dir ../example_data/kitty/train \
                              --expname kitty \
                              --nepoch 2000 --max_niter 200001 \
                              --gamma 1.0
cd code
# use same lighting as training
python evaluation/eval.py --conf confs_sg/default.conf \
                              --data_split_dir ../example_data/kitty/test \
                              --expname kitty \
                              --gamma 1.0 --resolution 256 --save_exr
# plug in new lighting                              
python evaluation/eval.py --conf confs_sg/default.conf \
                              --data_split_dir ../example_data/kitty/test \
                              --expname kitty \
                              --gamma 1.0 --resolution 256 --save_exr \
                              --light_sg ./envmaps/envmap3_sg_fit/tmp_lgtSGs_100.npy

Tips: for viewing exr images, you can use tev hdr viewer.

Some important pointers

Prepare your own data

Acknowledgements: this codebase borrows a lot from the awesome IDR work; we thank the authors for releasing their code.