Light Source Selection in Primary-Sample-Space Neural Photon Sampling

  • 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: Our photon sampling is based a normalizing flow that is conditioned by a feature vector representing a light index. The conditioning allows us to represent a discrete probability distribution for light source selection in photon mapping, which is difficult by conventional neural importance sampling without the conditioning.

Author(s)/Presenter(s):
Yuta Tsuji, Waseda University, Japan
Tatsuya Yatagawa, The University of Tokyo, Japan
Shigeo Morishima, Waseda University, Japan

Back

sq-ad
VRST