Denoising Your Monte Carlo Renders: Recent Advances in Image-Space Adaptive Sampling and Reconstruction


Denoising Your Monte Carlo Renders: Recent Advances in Image-Space Adaptive Sampling and Reconstruction

Tuesday, 11 August 2:00 PM - 3:30 PM | Los Angeles Convention Center, Room 404AB

With the ongoing shift in the computer graphics industry toward Monte Carlo rendering, there is a need for effective, practical noise-reduction techniques that are applicable to a wide range of rendering effects and easily integrated into
existing production pipelines.

This course surveys recent advances in image-space adaptive sampling and reconstruction algorithms for noise reduction, which have proven very effective at reducing the computational cost of Monte Carlo techniques in practice. These approaches leverage advanced image-filtering techniques with statistical methods for error estimation. They are attractive because they can be integrated easily into conventional Monte Carlo rendering frameworks, they are applicable to most rendering effects, and their computational overhead is modest.

Course Schedule

2 pm

2:15 pm
Leveraging General Image-Denoising Algorithms For MC Denoising

2:22 pm
Filtering The Noise From The Random Parameters In Monte Carlo

2:32 pm
Cross-Bilateral and NL-Means Filtering With SURE-Based Error Estimation and Feature Pre-Filtering

2:52 pm
Local Weighted Regression With Explicit Bias and Variance Estimation

3:12 pm
Using Machine Learning to Learn Optimal Filter Parameters

3:20 pm




Familiarity with rendering and basic concepts of Monte Carlo integration as implemented in modern rendering systems.

Intended Audience

Industry professionals interested in recent advances in adaptive sampling and reconstruction for reducing the noise of Monte Carlo rendering. Researchers interested in open research challenges and opportunities for future work.


Pradeep Sen
University of California, Santa Barbara

Mathias Zwicker
University of Bern

Fabrice Rousselle
Disney Research

Sung-Eui Yoon
Korea Advanced Institute of Science and Technology

Nima Khademi Kalantari
University of California, Santa Barbara