“Denoising-aware Adaptive Sampling for Monte Carlo Ray Tracing” by Firmino, Frisvad and Jensen

  • ©Arthur Firmino, Jeppe Revall Frisvad, and Henrik Wann Jensen

Conference:


Type:


Title:

    Denoising-aware Adaptive Sampling for Monte Carlo Ray Tracing

Session/Category Title: Neural Light Transport


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    We present an adaptive sampling technique for Monte Carlo rendering when combined with learning-based denoisers. Our technique requires no additional learning and is based on a novel estimate of a neural network’s output variance. Applying this to pre-existing denoisers and recent consistent post-correction techniques, we achieve faster error convergence.


ACM Digital Library Publication:



Overview Page: