Paper Info
Title
Nonlinearly Weighted First-order Regression for Denoising Monte Carlo Renderings.
Abstract
We address the problem of denoising Monte Carlo renderings by studying existing approaches and proposing a new algorithm that yields state-of-the-art performance on a wide range of scenes. We analyze existing approaches from a theoretical and empirical point of view, relating the strengths and limitations of their corresponding components with an emphasis on production requirements. The observations of our analysis instruct the design of our new filter that offers high-quality results and stable performance. A key observation of our analysis is that using auxiliary buffers (normal, albedo, etc.) to compute the regression weights greatly improves the robustness of zero-order models, but can be detrimental to first-order models. Consequently, our filter performs a first-order regression leveraging a rich set of auxiliary buffers only when fitting the data, and, unlike recent works, considers the pixel color alone when computing the regression weights. We further improve the quality of our output by using a collaborative denoising scheme. Lastly, we introduce a general mean squared error estimator, which can handle the collaborative nature of our filter and its nonlinear weights, to automatically set the bandwidth of our regression kernel.
Year
DOI
Venue
2016
10.1111/cgf.12954
Comput. Graph. Forum
Field
DocType
Volume
Computer science,Mean squared error,Robustness (computer science),Theoretical computer science,Artificial intelligence,Kernel (linear algebra),Computer vision,Monte Carlo method,Algorithm,Filter (signal processing),Bandwidth (signal processing),Pixel,Estimator
Journal
35
Issue
ISSN
Citations 
4
0167-7055
23
PageRank 
References 
Authors
0.85
31
8
Name
Order
Citations
PageRank
Benedikt Bitterli1513.92
Fabrice Rousselle227612.23
Bochang Moon318310.81
José Antonio Iglesias Guitián420411.77
David Adler5442.17
Kenny Mitchell621623.95
Wojciech Jarosz7104160.39
Jan Novák828617.42