Adobe, Inc.

Other

Czech Technical University in Prague

Paul John Asente

Jingwan Lu

Jakub Fiser

Teri Pettit

Elya Shechtman

Daniel Sýkora

Ondrej Jamriska

Darin C Tomack

Frank Guinan

Michal Lukác

Jose Ignacio Echevarria Vallespi

Michael D Schuster

Scott David Cohen

Brian Lynn Price

Stephen N Schiller

Mehmet Yumer

Michal Lukac

Cuong D Nguyen

Lesley Ann Northam

Radomir Mech

David P Simons

Michael F Kraley

Paul A George

Pierre Louveaux

Robert S Sargent

Elya Schechtman

Dafang He

Craig Kaplan

Xiao Yang

Zhaowen Wang

Franck Dernoncourt

Lubomir D Bourdev

Gavin Stuart Peter Miller

Li-Yi Wei

Shawn Alan Gaither

Xiaoyi Wang

Nedim Lipka

Chang Liu

Richard J Cohn

Qi Sun

Stephen Diverdi

Eylon Stroh

William F Kraus

Talin Chris Wadsworth

Daniel John Vogel

Rubaiat Habib Kazi

Verena Sabine Kaynig-Fittkau

Zeyu Wang

Reza Adhitya Saputra

Lena Edith Elfriede Gieseke

Germán Ariel Leiva

Emily Seminerio

Shayan Chandrashekar

Sangeeta Varma

Cheryl Lao

Spyridon Ampanavos

Huy Phan

Valerie Lina Head

Rachel Franz

Smitha Bangalore Naresh

Amirreza Shirani

Thamar I Solorio Martinez

Embodiments are disclosed for recommending fonts based on text inputs are described. In some embodiments, a method of recommending fonts includes receiving a selection of text, providing a representation of the selection of text to a font recommendation model, generating, by the font recommendation model, a prediction score for each of a plurality of fonts based on the representation of the selection of text, and returning at least one recommended font based on the prediction score for each of the plurality of fonts.

Context-aware font recommendation from text

Techniques for responsive video canvas generation are described to impart three-dimensional effects based on scene geometry to two-dimensional digital objects in a two-dimensional design environment. A responsive video canvas, for instance, is generated from input data including a digital video and scene data. The scene data describes a three-dimensional representation of an environment and includes a plurality of planes. A visual transform is generated and associated with each plane to enable digital objects to interact with the underlying scene geometry. In the responsive video canvas, an edit positioning a two-dimensional digital object with respect to a particular plane of the responsive video canvas is received. A visual transform associated with the particular plane is applied to the digital object and is operable to align the digital object to the depth and orientation of the particular plane. Accordingly, the digital object includes visual features based on the three-dimensional representation.

Responsive video canvas generation

Methods, systems, and non-transitory computer readable media are disclosed for intelligently generating partially textured accessible images. In one or more embodiments, the disclosed systems generate or access a color texture map specific to a given color vision deficiency. For example, the disclosed systems generate a color texture map that divides a color space into one or more textured segment of colors and one or more complementary untextured segments of colors. The disclosed systems can utilize the color texture map to intelligently apply different textures to subsets of pixels that contribute to color vision deficiency confusion. For example, the disclosed system maps pixels from a color image to the color texture map to identify a first subset of pixels corresponding to the textured segment of colors. The disclosed system generates a partially textured accessible image by applying a texture to the first subset of pixels.

Partially texturizing color images for color accessibility

In implementations of systems for augmented reality authoring of remote environments, a computing device implements an augmented reality authoring system to display a three-dimensional representation of a remote physical environment on a display device based on orientations of an image capture device. The three-dimensional representation of the remote physical environment is generated from a three-dimensional mesh representing a geometry of the remote physical environment and digital video frames depicting portions of the remote physical environment. The augmented reality authoring system receives input data describing a request to display a digital video frame of the digital video frames. A particular digital video frame of the digital video frames is determined based on an orientation of the image capture device relative to the three-dimensional mesh. The augmented reality authoring system displays the particular digital video frame on the display device.

Systems for augmented reality authoring of remote environments

Utilizing a visual-feature-classification model to generate font maps that efficiently and accurately organize fonts based on visual similarities. For example, extracting features from fonts of varying styles and utilize a self-organizing map (or other visual-feature-classification model) to map extracted font features to positions within font maps. Further, magnifying areas of font maps by mapping some fonts within a bounded area to positions within a higher-resolution font map. Additionally, navigating the font map to identify visually similar fonts (e.g., fonts within a threshold similarity).

Organizing and representing a collection of fonts according to visual similarity utilizing machine learning

In aspects of text importance spatial layout, a computing device implements a processing device to receive a text importance vector that includes designations of visual properties for constituent words of a text phrase. Spatial layouts of the text phrase are determined, with each spatial layout being a different displayable representation of the constituent words arranged based on the designations of the visual properties in the text importance vector for each of the constituent words. Feature vectors are generated, each feature vector represents a spatial layout of the text phrase and includes measurement properties of each of the constituent words in the respective spatial layout. The spatial layouts are ranked based on a metric that indicates a degree of similarity of the measurement properties of each of the constituent words in a respective spatial layout matching to the visual properties for the constituent words as designated in the text importance vector.

Text importance spatial layout

Techniques are provided for identifying structural elements of a document. One Methodology includes generating a first channel of rasterized content by rasterizing a full page of the document and generating one or more additional channels of rasterized content from the page of the document by rasterizing one or more corresponding content types from the page of the document. Each of the one or more additional channels includes a specific type of content that is different from each of the other one or more additional channels. The methodology further includes inputting the first channel of rasterized content and the one or more additional channels of rasterized content into a machine learning (ML) model. The methodology continues with determining location and classification for each of a plurality of structural elements on the page of the document using the ML model.

Multiple channels of rasterized content for page decomposition using machine learning

Disclosed systems and methods categorize text regions of an electronic document into document object types based on a combination of semantic information and appearance information from the electronic document. A page segmentation application executing on a computing device provides a textual feature representation and a visual feature representation to a neural network. The application identifies a correspondence between a location of the set of pixels in the electronic document and a location of a particular document object type in an output page segmentation. The application further outputs a classification of the set of pixels as being the particular document object type based on the identified correspondence.

Semantic page segmentation of vector graphics documents

In implementations of augmented video prototyping, a mobile device records augmented video data as a captured video of a recorded scene in an environment, the augmented video data including augmented reality tracking data as 3D spatial information relative to objects in the recorded scene. A video prototyping module localizes the mobile device with reference to the objects in the recorded scene using the 3D spatial information for the mobile device being within boundaries of the recorded scene in the environment. The video prototyping module can generate an avatar for display that represents the mobile device at a current location from a perspective of the recorded scene, and create a spatial layer over a video frame at the current location of the avatar that represents the mobile device. The spatial layer is an interactive interface on which to create an augmented reality feature that displays during playback of the captured video.

Augmented video prototyping

Methods and systems disclosed herein relate generally to systems and methods for transforming document elements in response to modifications to a layout of a document. A layout-modification application identifies, from a first document having a first document layout, a first set of measurements of a document element and a first location of the document element within the first document. Based on an aspect-ratio difference between the first document layout and a second document layout, the layout-modification application selects a set of transformation rules that specify, for the document element, a second set of measurements and a second location within a second document. To select the particular set of transformation rules, the layout-modification application uses the determined aspect-ratio difference. The layout-modification application applies the selected set of transformation rules to the document element.

Transforming document elements for modified document layouts

Methods and systems for aiding users in generating object pattern designs with increased speed. In particular, one or more embodiments train a sequence-based machine-learning model using training objects, each training object including a plurality of regions with a plurality of design elements. One or more embodiments identify a plurality regions of an object with a first region adjacent a second region. One or more embodiments receive a user selection of a design element for populating the first region with a first design element from a plurality of design elements. One or more embodiments identify a second design element from the plurality of design elements based on the first design element using the trained sequence-based machine-learning model. One or more embodiments also populate the second region with one or more instances of the second design element.

Recommending pattern designs for objects using a sequence-based machine-learning model

Freeform drawing beautification techniques are described. An input is received by a computing device describing a freeform path drawn by a user as part of a drawing, the freeform path not formed solely as a circular arc or a circle (e.g., a fixed distance from a point) and including one or more curved elements. The drawing is examined by the computing device to locate another curved element in the drawing. One or more suggestions are constructed to adjust the freeform path by the computing device based on the located curved element in the drawing. The constructed one or more suggestions are output to adjust the freeform path by the computing device.

Freeform drawing beautification

Methods and systems are provided for performing dynamic mapping between a virtual environment and a real-world space. During dynamic mapping, a current virtual scene of the virtual environment that is within view of a user is prioritized over areas of the virtual environment that are out of view. The dynamic mapping between the virtual environment and the real-world space can be utilized to render a virtual scene for user in real-time. As a user interacts and/or moves within the virtual environment, dynamic mapping can be performed in real-time to capture any dynamic changes to the real-world space and/or the virtual environment.

Dynamic mapping of virtual and physical interactions

A design layout recommendation system is disclosed that evaluates layouts of design elements generated based on aspect ratios and relative areas. In an embodiment, the system enumerates possible arrangements of the design elements into columns or rows based on a layout preference. The system can then construct layouts of the design elements for each enumerated arrangement of the design elements based on relative areas of the design elements. The layouts of the design elements are in column-oriented reading order or row-oriented reading order based on the layout preference. The system can then recommend at least one layout of the design elements based on selection criteria.

Layout of design elements in electronic documents

Certain embodiments involve generating one or more of appearance guide and a positional guide and using one or more of the guides to synthesize a stylized image or animation. For example, a system obtains data indicating a target image and a style exemplar image. The system generates an appearance guide, a positional guide, or both from the target image and the style exemplar image. The system uses one or more of the guides to transfer a texture or style from the style exemplar image to the target image.

Generating a stylized image or stylized animation by matching semantic features via an appearance guide, a segmentation guide, and/or a temporal guide

Growing community of inventors

Redwood City, CA, United States of America

Paul John Asente