J
Jan Novák
Researcher at Disney Research
Publications - 48
Citations - 2087
Jan Novák is an academic researcher from Disney Research. The author has contributed to research in topics: Rendering (computer graphics) & Artificial neural network. The author has an hindex of 22, co-authored 48 publications receiving 1610 citations. Previous affiliations of Jan Novák include Walt Disney Animation Studios & Karlsruhe Institute of Technology.
Papers
More filters
Journal ArticleDOI
Kernel-predicting convolutional networks for denoising Monte Carlo renderings
Steve Bako,Thijs Vogels,Brian McWilliams,Mark Meyer,Jan Novák,Alex Harvill,Pradeep Sen,Tony DeRose,Fabrice Rousselle +8 more
TL;DR: A novel, supervised learning approach that allows the filtering kernel to be more complex and general by leveraging a deep convolutional neural network (CNN) architecture and introduces a novel, kernel-prediction network which uses the CNN to estimate the local weighting kernels used to compute each denoised pixel from its neighbors.
Journal ArticleDOI
Neural Importance Sampling
TL;DR: In this paper, deep neural networks are used for generating samples in Monte Carlo integration with unnormalized stochastic estimates of the target distribution, based on nonlinear independent components estimation (NICE).
Journal ArticleDOI
Denoising with kernel prediction and asymmetric loss functions
Thijs Vogels,Fabrice Rousselle,Brian McWilliams,Gerhard Rothlin,Alex Harvill,David Adler,Mark Meyer,Jan Novák +7 more
TL;DR: A theoretical analysis of convergence rates of kernel-predicting architectures is presented, shedding light on why kernel prediction performs better than synthesizing the colors directly, complementing the empirical evidence presented in this and previous works.
Proceedings Article
Scalable Realistic Rendering with Many-Light Methods.
TL;DR: This report aims to give an easy-to-follow, introductory tutorial of many-light theory, provide a comprehensive, unified survey of the topic with a comparison of the main algorithms, and present a vision to motivate and guide future research.
Journal ArticleDOI
Practical Path Guiding for Efficient Light-Transport Simulation
TL;DR: This work proposes an adaptive spatio‐directional hybrid data structure, referred to as SD‐tree, for storing and sampling incident radiance, and presents a principled way to automatically budget training and rendering computations to minimize the variance of the final image.