“Neural Parametric Mixtures for Path Guiding” by Dong, Wang and Li

  • ©Honghao Dong, Guoping Wang, and Sheng Li

Conference:


Type:


Title:

    Neural Parametric Mixtures for Path Guiding

Session/Category Title:   Neural Light Transport


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    We present Neural Parametric Mixtures (NPM), a neural formulation to encode target distributions for path guiding. NPM uses a continuous and compact representation for encoding parametric distributions and decodes them via lightweight MLPs. Gradient-based optimization strategy can efficiently train NPM while being practical for parallelization on GPUs.


Overview Page: