Presentation
Path Graphs: Iterative Path Space Filtering
Event Type
Technical Papers
TimeFriday, December 1711:22am - 11:33am JST
LocationHall B5 (1) (5F, B Block) & Virtual Platform
DescriptionTo render higher quality images from the samples generated by path tracing with a very low sample count, we propose
a novel path-space filtering approach that
processes a fixed collection of paths to
refine and improve radiance estimates throughout the scene.
Our method operates on a \emph{path graph} consisting of the union of the traced paths with additional neighbor edges inserted between spatially nearby vertices.
The approach refines the initial noisy radiance estimates via an aggregation operator, which effectively treats direct and indirect radiance estimates on neighboring path vertices as independent sampling techniques and combines them using well-chosen weights.
We also introduce a propagation operator to forward the refined estimates along the paths to successive bounces. We apply the aggregation and propagation operations to the graph iteratively, progressively refining the radiance estimates, converging to fixed-point radiance estimates with lower variance than the original ones.
Our approach is lightweight, in the sense that it can be easily plugged into any standard path tracer and neural final image denoiser. Furthermore, it is independent of scene complexity, as the graph size only depends on image resolution and average path depth.
We demonstrate that our technique leads to realistic rendering results starting from as low as 1 path per pixel, even in complex indoor scenes dominated by multi-bounce indirect illumination.
a novel path-space filtering approach that
processes a fixed collection of paths to
refine and improve radiance estimates throughout the scene.
Our method operates on a \emph{path graph} consisting of the union of the traced paths with additional neighbor edges inserted between spatially nearby vertices.
The approach refines the initial noisy radiance estimates via an aggregation operator, which effectively treats direct and indirect radiance estimates on neighboring path vertices as independent sampling techniques and combines them using well-chosen weights.
We also introduce a propagation operator to forward the refined estimates along the paths to successive bounces. We apply the aggregation and propagation operations to the graph iteratively, progressively refining the radiance estimates, converging to fixed-point radiance estimates with lower variance than the original ones.
Our approach is lightweight, in the sense that it can be easily plugged into any standard path tracer and neural final image denoiser. Furthermore, it is independent of scene complexity, as the graph size only depends on image resolution and average path depth.
We demonstrate that our technique leads to realistic rendering results starting from as low as 1 path per pixel, even in complex indoor scenes dominated by multi-bounce indirect illumination.
