search

gsrelight / gs-relight

Official Code Release for SIGGRAPH Asia 2024 Paper: GS^3: Efficient Relighting with Triple Gaussian Splatting
GNU General Public License v3.0
95 stars 7 forks source link

Question Regarding Shadow Splatting for Area and Parallel Light Sources #6

Open HarryPeverell opened 6 days ago

HarryPeverell commented 6 days ago

Hi ,

First of all, I would like to express my gratitude for the excellent work you've done on this project. It’s truly impressive, and I’ve found your approach to be very insightful.

I have a question regarding the dataset used in the project. It seems that the dataset is designed with point light sources in mind. I was wondering how the Shadow Splatting technique would be adapted if the light source were an area light source instead? Furthermore, if the light rays are parallel (as in the case of distant light sources or sunlight), how should the Shadow Splatting calculation be adjusted?

Could you please share the necessary modifications to the workflow for handling such changes in the light source? Any guidance on this would be greatly appreciated.

I look forward to your response, and thank you again for your great work.

Best regards,
Harry

RupertPaoZ commented 3 days ago

You can simulate parallel light from infinity by using a directional light, such as modifying the camera model for the shadow splatting to an orthographic projection model, or directly using a point light source from a very distant location as an approximation.