Denoising with Kernel Prediction and
Asymmetric Loss Functions

Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Gerhard Röthlin, Alex Harvill, David Adler, Mark Meyer, Jan Novák

Denoising

Monte Carlo path tracing

Input

Denoised

Kernel Prediction

Basic single-frame denoiser (Bako et al.  2017)

Kernel
x
Image
=
Color

© Disney

Features

  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

Features

  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

Multi-renderer support

Baseline generalization ability

Renderer B Input
Trained on Renderer A data
Retrained on Renderer B data

Scene by nacimus (Blendswap)

Multi-renderer support

Source-aware encoders

Multi-renderer support

Data efficiency of encoder training

  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

Noisy input (32 SPP)

Denoised (still frames)

Denoised (7 frame temporal window)

Temporal denoising

Reusing a pre-trained single-frame denoiser

(Chaitanya et al. 2017)
  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

Multi-scale denoising

© Disney

Multi-scale denoising

Cheaper denoising of low frequencies

Multi-scale denoising

© Disney

  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

Adaptive sampling

with an error predictor

Predicted sampling map

  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

© Disney / Pixar

Loss Darker Brighter Input Ref

Summing up …

  • Multi-renderer support source-aware encoders
  • Temporal stability cross-frame denoising
  • Denoising of low frequencies a multi-scale approach
  • Adaptive sampling the error predictor
  • User control asymmetric loss functions

Input

Denoised

Input

Denoised

Input

Denoised

Input

Denoised