Presentation

Photon-driven Neural Reconstruction for Path Guiding
Presenter
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
Virtual
Registration Categories
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Time
Location
DescriptionWe present a path-guiding approach that can reconstruct high-quality sampling distributions using an offline trained neural network. We leverage photons traced from light sources for sampling density reconstruction, which is effective for challenging scenes with global illumination. We further partition the scene space into an adaptive hierarchical grid.