Presentation
Ragged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings
SessionLight Transport
DescriptionRaNAD is the first spatiotemporal neural denoiser for deep Monte Carlo renderings. It handles semi-structured deep images with variable bin counts per pixel through ragged neighborhood attention, and exploits temporal context across up to seven frames, greatly advancing in both quality and temporal stability for denoising deep images.
Event Type
Technical Paper
TimeTuesday, 21 July 20262:30pm - 2:40pm PDT
LocationRoom 408 A
Digital Library
PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 20262:00pm - 3:30pm PDTRoom 408 A
Artificial Intelligence/Machine Learning
Rendering
Full Conference Supporter
Full Conference
