Official Implementation for BSDF importance sampling using a diffusion model
SIGGRAPH Asia 2024 (conference track)
Currently, I've simply cleaned up my old experimental code and placed it here. I plan to write a cleaner version with comprehensive instructions and annotations later(It now seems to be much longer than I thought... I failed with my PhD application and now try to get a job... I'll complete this repo once I settle down.)
However, the code provided here should already be functional and capable of reproducing the results presented in our paper.
If you'd like to use or compare with our model, or if you have any questions, please don't hesitate to email me!
For guys interested in our work, we recommend checking our 1D toy case demo.
This simple demo effectively showcases the key concepts and should be enjoyable to go through. Plus, it’s quick and won’t take much of your time!