Disney Enterprises, Inc.

Eidgenossische Technische Hochschule Zurich

Samsung Electronics Co., Ltd.

The University of North Carolina at Chapel Hill

Eth Zurich

Eth Zürich (Eidgenossische Technische Hochscule Zürich)

Liberovision Ag

Vizrt Ag

Markus Gross

Alexander Sorkine Hornung

Robert Walker Sumner

Stelian Coros

Do Kyoon Kim

Tunc Ozan Aydin

Bernd Bickel

Nikolce Stefanoski

Jae Young Sim

Sasha Anna Schriber

Simone Croci

Bernhard Thomaszewski

Anselm Grundhofer

Lanny Starkes Smoot

Oliver Wang

Christopher Richard Schroers

Derek Edward Bradley

Quinn Smithwick

Gioacchino Noris

Thabo D Beeler

Paul A Beardsley

Aljoscha Smolic

Jeong Hwan Ahn

Alexandre Chapiro

Wojciech Matusik

Hanspeter Pfister

Marc Stewart Levoy

Hyun Jung Shim

Aljosa Aleksej Andrej Smolic

Brian Whited

Simon Heinzle

Max Grosse

Maryann Simmons

Ahmet Cengiz Öztireli

Kee Chang Lee

Abdelaziz Djelouah

Henry Fuchs

Aljosa A Smolic

Henning Zimmer

Daniel James Reetz

Mubbasir Kapadia

Ariel Shamir

Manuel Lang

Nicola V Ranieri

Amit Bermano

Fabian Hahn

Isabel Simo

Mario Botsch

Rolf Adelsberger

Daisuke Iwai

Sebastian Martin

Daniel Sykora

Philipp Bruschweiler

Gael Guennebaud

Robert Carnecky

Daniel Inversini

Quinn Yorklun Jen Smithwick

Maurizio Nitti

Yael Pritch

Marc Pollefeys

Yeara Kozlov

Remo Ziegler

Simone Meyer

Marcel Germann

Richard Keiser

Pelin Dogan

Daniel Cotting

Christoph Niederberger

Leonid Sigal

Fabian Andreas Hahn

Wojciech Witon

Victor Cornillere

Eleftheria Tsipidi

Jan Ruegg

Justine Fung

Carolina Ferrari

Bob Sumner

Yongzhe Wang

Kae Chang Lee

Martin Naef

Katherine Watson

Marco Ancona

Nam Wook Kim

Hagen Friedrich Seifert

Rushit Sanghrajka

Frederik Rudolf Mutzel

Jereon Van Baar

Aljosa Smolic

Tiberiu Popa

Stephan Würmlin Stadler

In various embodiments, a phrase grounding model automatically performs phrase grounding for a source sentence and a source image. The phrase grounding model determines that a first phrase included in the source sentence matches a first region of the source image based on the first phrase and at least a second phrase included in the source sentence. The phrase grounding model then generates a matched pair that specifies the first phrase and the first region. Subsequently, one or more annotation operations are performed on the source image based on the matched pair. Advantageously, the accuracy of the phrase grounding model is increased relative to prior art solutions where the interrelationships between phrases are typically disregarded.

Techniques for performing contextual phrase grounding

In various embodiments, a relevance application quantifies how a trained neural network operates. In operation, the relevance application generates a set of input distributions based on a set of input points associated with the trained neural network. Each input distribution is characterized by a mean and a variance associated with a different neuron included in the trained neural network. The relevance application propagates the set of input distributions through a probabilistic neural network to generate at least a first output distribution. The probabilistic neural network is derived from at least a portion of the trained neural network. Based on the first output distribution, the relevance application computes a contribution of a first input point included in the set of input points to a difference between a first output point associated with a first output of the trained neural network and an estimated mean prediction associated with the first output.

Techniques for understanding how trained neural networks operate

The present disclosure generally relates to a projection system with increased spatial resolution. The projection system includes one or more light sources, a spatial light modulator configured to reflect light received from the one or more light sources to generate a plurality of sub-images of a composite image, and an optical system configured to reflect each of the plurality of sub-images the sub-images at a different portion of a projection surface. By projecting the single composite image using a plurality of sub-images projected at different times and/or locations from one another, the composite full image has a higher resolution as compared to the resolution defined by the hardware of the spatial light modulator and light sources.

System and method for increased spatial resolution

Systems and methods are provided for a workflow framework that scriptwriters can utilize when developing scripts. A script can be parsed to identify one or more elements in a script, and various visual representations of the one or more elements and/or a scene characterized in the script can be automatically generated. A user may develop or edit the script which can be presented in a visual and temporal manner. Information parsed from the script can be stored in basic information elements, and used to create a knowledge bases.

Automated storyboarding based on natural language processing and 2D/3D pre-visualization

Novel systems and methods are described for creating, compressing, and distributing video or image content graded for a plurality of displays with different dynamic ranges. In implementations, the created content is 'continuous dynamic range' (CDR) content&#x2014;a novel representation of pixel-luminance as a function of display dynamic range. The creation of the CDR content includes grading a source content for a minimum dynamic range and a maximum dynamic range, and defining a luminance of each pixel of an image or video frame of the source content as a continuous function between the minimum and the maximum dynamic ranges. In additional implementations, a novel graphical user interface for creating and editing the CDR content is described.

Methods for creating and distributing art-directable continuous dynamic range video

In particular embodiments, a 2D representation of an object may be provided. A first method may comprise: receiving sketch input identifying a target position for a specified portion of the object; computing a deformation for the object within the context of a character rig specification for the object; and displaying an updated version of the object. A second method may comprise detecting sketch input; classifying the sketch input, based on the 2D representation, as an instantiation of the object; instantiating the object using a 3D model of the object; and displaying a 3D visual representation of the object.

Sketch-based abstraction for character posing and synthesis

According to one implementation, a system for visualizing media content includes a computing platform including a hardware processor and a system memory, storing a content visualization software code. The hardware processor is configured to execute the content visualization software code to receive a media file, parse the media file to identify a primary content and metadata describing the primary content, and analyze the metadata to determine representative features of the primary content. The hardware processor further executes the content visualization software code to generate a circular visual representation of the primary content based on the metadata and the representative features, the circular visual representation having a non-linear correspondence to at least one of the representative features. The circular visual representation includes a central circle having a central radius, and multiple, at least semicircular segments, each having a respective radius greater than the central radius.

Circular visual representation of media content

According to one implementation, a narrative visualization system includes a computing platform having a hardware processor and a system memory storing a narrative visualization software code. The hardware processor is configured to execute the narrative visualization software code to receive multiple media files. For each of the media files, the hardware processor is further configured to execute the narrative visualization software code to parse the media file to identify a primary content and metadata describing the primary content, to analyze the metadata to determine representative features of the primary content, and to generate a visualization of the primary content based on the metadata and the representative features. The visualization depicts a temporal flow of the primary content in a story tune of the primary content in apposition to a temporal flow of the primary content in a narrative time of the primary content.

Narrative visualization system

A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.

Video color propagation

An image processor inputs a first image and outputs a downscaled second image by upscaling the second image to a third image, wherein the third image is substantially the same size as the first image size with a third resolution, associating pixels in the second image with a corresponding group of pixels from the third set of pixels, sampling a first image area at a first location of the first set of pixels to generate a first image sample, sampling a second image area of the third set of pixels to generate a second image sample, measuring similarity between the image areas, generating a perceptual image value, recursively adjusting values of third set of pixels until the image perception value matches a perceptual standard value, and adjusting pixel values in the second image to a representative pixel value of each of the corresponding group of pixels.

Image processing system for downscaling images using perceptual downscaling method

There are provided systems and methods for an interactive synchronization of multiple videos. An example system includes a memory storing a first video and a second video, the first video including first video clips and the second video including second video clips. The system further includes a processor configured to calculate a histogram based on a number of features that are similar between the first video clips and the second video clips, generate a cost matrix based on the histogram, generate a first graph that includes first nodes based on the cost matrix, compute a path through the graph using the nodes, and align the first video with the second video using the path, where the path corresponds to playback speeds for the first video and the second video.

Interactive synchronization of multiple videos

A system for augmenting the appearance of an object including a plurality of projectors. Each projector includes a light source and a lens in optical communication with the light source, where the lens focuses light emitted by the light source on the object. The system also includes a computer in communication with the plurality of projectors, the computer including a memory component and a processing element in communication with the memory component and the plurality of projectors. The processing element determines a plurality of images to create an augmented appearance of the object and provides the plurality of images to the plurality of projectors to project light corresponding to the plurality of images onto the object to create the augmented appearance of the object. After the images are projected onto the object, the augmented appearance of the objected is substantially the same regardless of a viewing angle for the object.

Augmenting physical appearance using illumination

A method is disclosed for applying physics-based simulation to an animator provided rig. The disclosure presents equations of motions for simulations performed in the subspace of deformations defined by an animator's rig. The method receives an input rig with a plurality of deformation parameters, and the dynamics of the character are simulated in the subspace of deformations described by the character's rig. Stiffness values defined on rig parameters are transformed to a non-homogeneous distribution of material parameters for the underlying rig.

Fast rig-based physics simulation

Growing community of inventors

Zurich, Switzerland

Markus Gross