Patents by Inventor Brian McWilliams
Brian McWilliams has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10491856Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a frame interpolation software code, the frame interpolation software code including a convolutional neural network (CNN) trained using a loss function having an image loss term summed with a phase loss term. The hardware processor executes the frame interpolation software code to receive first and second consecutive video frames including respective first and second images, and to decompose the first and second images to produce respective first and second image decompositions. The hardware processor further executes the frame interpolation software code to use the CNN to determine an intermediate image decomposition corresponding to an interpolated video frame for insertion between the first and second video frames based on the first and second image decompositions, and to synthesize the interpolated video frame based on the intermediate image decomposition.Type: GrantFiled: May 8, 2018Date of Patent: November 26, 2019Assignees: Disney Enterprises, Inc., ETH ZurichInventors: Christopher Schroers, Simone Meyer, Abdelaziz Djelouah, Alexander Sorkine Hornung, Brian McWilliams, Markus Gross
-
Patent number: 10475165Abstract: Supervised machine learning using convolutional neural network (CNN) is applied to denoising images rendered by MC path tracing. The input image data may include pixel color and its variance, as well as a set of auxiliary buffers that encode scene information (e.g., surface normal, albedo, depth, and their corresponding variances). In some embodiments, a CNN directly predicts the final denoised pixel value as a highly non-linear combination of the input features. In some other embodiments, a kernel-prediction neural network uses a CNN to estimate the local weighting kernels, which are used to compute each denoised pixel from its neighbors. In some embodiments, the input image can be decomposed into diffuse and specular components. The diffuse and specular components are then independently preprocessed, filtered, and postprocessed, before recombining them to obtain a final denoised image.Type: GrantFiled: November 15, 2017Date of Patent: November 12, 2019Assignees: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule ZürichInventors: Thijs Vogels, Jan Novák, Fabrice Rousselle, Brian McWilliams
-
Publication number: 20190304069Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.Type: ApplicationFiled: July 31, 2018Publication date: October 3, 2019Applicants: Pixar, Disney Enterprises, Inc.Inventors: Thijs Vogels, Fabrice Rousselle, Jan Novak, Brian McWilliams, Mark Meyer, Alex Harvill, David Adler
-
Publication number: 20190304067Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.Type: ApplicationFiled: July 31, 2018Publication date: October 3, 2019Applicants: Pixar, Disney Enterprises, Inc.Inventors: Thijs Vogels, Fabrice Rousselle, Jan Novak, Brian McWilliams, Mark Meyer, Alex Harvill, David Adler
-
Publication number: 20190304068Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.Type: ApplicationFiled: July 31, 2018Publication date: October 3, 2019Applicants: Pixar, Disney Enterprises, Inc.Inventors: Thijs Vogels, Fabrice Rousselle, Jan Novak, Brian McWilliams, Mark Meyer, Alex Harvill
-
Publication number: 20190289257Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a frame interpolation software code, the frame interpolation software code including a convolutional neural network (CNN) trained using a loss function having an image loss term summed with a phase loss term. The hardware processor executes the frame interpolation software code to receive first and second consecutive video frames including respective first and second images, and to decompose the first and second images to produce respective first and second image decompositions. The hardware processor further executes the frame interpolation software code to use the CNN to determine an intermediate image decomposition corresponding to an interpolated video frame for insertion between the first and second video frames based on the first and second image decompositions, and to synthesize the interpolated video frame based on the intermediate image decomposition.Type: ApplicationFiled: May 8, 2018Publication date: September 19, 2019Inventors: Christopher Schroers, Simone Meyer, Abdelaziz Djelouah, Alexander Sorkine Hornung, Brian McWilliams, Markus Gross
-
Publication number: 20190130530Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a software code including an artificial neural network (ANN). The hardware processor is configured to execute the software code to receive a first video sequence having a first display resolution, and to produce a second video sequence based on the first video sequence using the ANN. The second video sequence has a second display resolution higher than the first display resolution. The ANN is configured to provide sequential frames of the second video sequence that are temporally stable and consistent in color to reduce visual flicker and color shifting in the second video sequence.Type: ApplicationFiled: February 1, 2018Publication date: May 2, 2019Inventors: Christopher Schroers, Yifan Wang, Federico Perazzi, Brian McWilliams, Alexander Sorkine Hornung
-
Publication number: 20180293711Abstract: Supervised machine learning using convolutional neural network (CNN) is applied to denoising images rendered by MC path tracing. The input image data may include pixel color and its variance, as well as a set of auxiliary buffers that encode scene information (e.g., surface normal, albedo, depth, and their corresponding variances). In some embodiments, a CNN directly predicts the final denoised pixel value as a highly non-linear combination of the input features. In some other embodiments, a kernel-prediction neural network uses a CNN to estimate the local weighting kernels, which are used to compute each denoised pixel from its neighbors. In some embodiments, the input image can be decomposed into diffuse and specular components. The diffuse and specular components are then independently preprocessed, filtered, and postprocessed, before recombining them to obtain a final denoised image.Type: ApplicationFiled: November 15, 2017Publication date: October 11, 2018Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Thijs Vogels, Jan Novák, Fabrice Rousselle, Brian McWilliams
-
Publication number: 20180293713Abstract: Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance sampling, where more challenging patches or patches including areas of particular interests within a training dataset are selected with higher probabilities than others. In some other embodiments, generative adversarial networks (GANs) may be used for training a machine-learning based denoiser as an alternative to using pre-defined loss functions.Type: ApplicationFiled: April 5, 2018Publication date: October 11, 2018Applicant: PIXARInventors: Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Mark Meyer, Jan Novak
-
Publication number: 20180293712Abstract: Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance sampling, where more challenging patches or patches including areas of particular interests within a training dataset are selected with higher probabilities than others. In some other embodiments, generative adversarial networks (GANs) may be used for training a machine-learning based denoiser as an alternative to using pre-defined loss functions.Type: ApplicationFiled: April 5, 2018Publication date: October 11, 2018Applicant: PIXARInventors: Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Mark Meyer, Jan Novak
-
Publication number: 20180293496Abstract: Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance sampling, where more challenging patches or patches including areas of particular interests within a training dataset are selected with higher probabilities than others. In some other embodiments, generative adversarial networks (GANs) may be used for training a machine-learning based denoiser as an alternative to using pre-defined loss functions.Type: ApplicationFiled: April 5, 2018Publication date: October 11, 2018Applicant: PIXARInventors: Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Mark Meyer, Jan Novak
-
Publication number: 20140034533Abstract: A system and method for packaging individual beverage containers is disclosed. A package of individual beverage containers includes a plurality of beverage cartons abutted at respective edge surfaces; each beverage carton contains a plurality of individual beverage containers. The beverage cartons are secured together by at least one resilient band that is disposed over and applies a force to secure together the plurality of beverage cartons.Type: ApplicationFiled: August 1, 2013Publication date: February 6, 2014Applicant: ANHEUSER-BUSCH, LLCInventors: Brian McWilliams, Jeff Krull, Todd Odehnal
-
Patent number: D756774Type: GrantFiled: August 15, 2014Date of Patent: May 24, 2016Inventor: Brian McWilliams