James-Stein Gradient Combiner for Inverse Monte Carlo Rendering

Jeongmin Gu, Bochang Moon

Overview

This repository provides the example codes for SIGGRAPH 2025 paper, James-Stein Gradient Combiner for Inverse Monte Carlo Rendering.

Requirements

We recommend running this code through Docker and Nvidia-docker on Ubuntu. Please refer to the detailed instruction for the installation of Docker and Nvidia-docker.

Test with example codes

For running the provided codes, you can proceed in the following order:

1. Build and run docker image

bash run_docker.sh

2. Build PyTorch custom operators (CUDA)

cd custom_ops
python setup_js.py install
python setup_filter.py install

3. Run the script

bash run_mts.sh

To test the Plane scene, you can download other scene components in this repository (Chang et al.).

Contact

If there are any questions, issues or comments, please feel free to send an e-mail to [email protected].