Monte Carlo Denoising with a Sparse Auxiliary Feature Encoder

  • Full Access Full Access
  • Onsite Student Access Onsite Student Access
  • Onsite Experience Onsite Experience
  • Virtual Full Access Virtual Full Access
  • Virtual Basic Access Virtual Basic Access

*All presentations are available in the virtual platform on-demand. The posters will also be exhibited onsite in Hall E, Tokyo International Forum from 15 – 17 December 2021.

Abstract: Denoising Monte Carlo path tracing requires utilizing auxiliary buffers efficiently. In this work, we introduce sparse convolutions to the auxiliary buffer encoder, largely reducing its computations without apparent performance drops.

Author(s)/Presenter(s):
Siyuan Fu, Center for Future Media, the Department of Computer Science and Engineering, University of Electronic Science and Technology of China, China
Yifan Lu, Center for Future Media, the Department of Computer Science and Engineering, University of Electronic Science and Technology of China, China
Xiao Hua Zhang, Hiroshima Institute of Technology, Japan
Ning Xie, Center for Future Media, the Department of Computer Science and Engineering, University of Electronic Science and Technology of China, China

Back

VRST
sq-ad