Adobe, Inc.

Apple Inc.

Gavin Stuart Peter Miller

Radomir Mech

Hailin Jin

Nathan Aaron Carr

Kevin Gary Smith

Kent Andrew Edmonds

Scott David Cohen

Jonathan Worthen Brandt

Eric M Hoffert

Zeke Koch

Walter Wei-Tuh Chang

Jen-Chan Jeff Chien

Peter Raymond Fransen

Thomas William Randall Jacobs

Zhe Lin

Xiaohui Shen

Zhaowen Wang

Govind P Balakrishnan

Yufei Wang

Brian Lynn Price

Walter Chang

Byungmoon Kim

Xuejun Xu

Emre Demiralp

John Bevil Bates

Yuyan Song

Grayson Squier Lang

Tenell Rhodes

Max Gray Edell

Henricus Cabanier

Matthew Keith Albright

Brian David Williams

Cory Lynn Edwards

Daicho Ito

Tenell Glen Rhodes, Jr

Tim Christopher Reiner

Fan Bao

James David Batson

Paul John Asente

Jose Ignacio Echevarria Vallespi

Li-Yi Wei

Mehmet Yumer

Stefano Koenig Corazza

Daichi Ito

Pushkar Prakash Joshi

Peter F Falco, Jr

Qi Sun

Christine Marie Dierk

Jacqueline L Feild

Kenji Enomoto

Embodiments are disclosed for generating an instant mask from polarized input images. A method of generating the mask includes obtaining, by a user interface manager, a set of polarized input images, the set of polarized images including background images depicting a background and subject images depicting a foreground object in front of the background and backlit by a polarized light source, the set of polarized input images including more than two polarized images, each associated with a different polarization angle, determining, by a matte optimization manager, an at least partially polarized reflection on the foreground object based on the set of polarized input images, determining, by the matte optimization manager, an alpha matte based at least on intensity values associated with each of the set of polarized input images such that the alpha matte isolates the foreground object and removes the at least partially polarized reflection, and generating, by a matte generator, an output matte based on the alpha matte.

Instant masks with polarized light

Methods and systems are provided for a three-dimensional effect on the edge of a multi-page document (e.g., a book). In one embodiment, a first set of image slices associated with a left-eye image is printed on a first side of long pages of a multi-page document. The first set of image slices printed adjacent to edges of the long pages. A second set of image slices associated with a right-eye image is printed on a second side of the long pages of the multi-page document. The second set of image slices printed adjacent to the edges of the long pages. Thereafter, the multi-page document is created by interleaving the long pages with short pages to enable visibility of the first set of image slices and the second set of image slices printed adjacent to the edges of the long pages.

Three-dimensional effect on edge of multi-page document

Application personalization techniques and systems are described that leverage an embedded machine learning module to preserve a user's privacy while still supporting rich personalization with improved accuracy and efficiency of use of computational resources over conventional techniques and systems. The machine learning module, for instance, may be embedded as part of an application to execute within a context of the application to learn user preferences to train a model using machine learning. This model is then used within the context of execution of the application to personalize the application, such as control access to digital content, make recommendations, control which items of digital marketing content are exposed to a user via the application, and so on.

Application digital content control using an embedded machine learning module

A control system for independent alternating-input ('IAI') devices includes multiple IAI devices and an analog switch component. The control system may also include a bus-generating component. The analog switch component includes multiple switches configured to connect of disconnect input connection points of the analog switch component and voltage input points of the IAI devices. The analog switch component opens or closes switches, responsive to a digital control signal, to provide voltage signals to the voltage input points of the IAI devices. In some cases, the IAI devices activate or deactivate based on the provided voltage signals. In some cases, the bus-generating component provides a first voltage signal to a first voltage input point of an IAI device, and the analog switch component controls the switches to provide a second voltage signal to a second voltage input point of the IAI device.

Control techniques for multiple alternating-input devices

Systems and methods are provided for providing a navigation interface to access or otherwise use electronic content items. In one embodiment, an augmentation application identifies at least one entity referenced in a document. The entity can be referenced in at least two portions of the document by at least two different words or phrases. The augmentation application associates the at least one entity with at least one multimedia asset. The augmentation application generates a layout including at least some content of the document referencing the at least one entity and the at least one multimedia asset associated with the at least one entity. The augmentation application renders the layout for display.

Augmenting text with multimedia assets

Embodiments provide traceability of edits to a document, i.e., a verifiable and immutable provenance chain for the document. Systems and methods enable traceability of edits, by encoding, for states of the document, a fingerprint (e.g., a cryptographic hash of the document's contents) and an edit history within a block written to a distributed ledger (e.g., a blockchain). The ledger is maintained via a self-organizing peer-to-peer distributed ledger network. Once added to the ledger, the contents of a block (e.g., the document's fingerprint and edit history) are immutable and the integrity of the edit history encoded in the ledger is secure. The algorithm that generates the fingerprint is sensitive to edits of the document. The non-corruptible fingerprint encoded in the ledger is employable to detect any edits that are not included in the encoded edit history and/or inconsistent with a currently available version of the document.

Traceability of edits to digital documents via distributed ledgers

Digital content control based on shared machine learning properties

Image compensation for an occluding direct-view augmented reality system is described. In one or more embodiments, an augmented reality apparatus includes an emissive display layer for presenting emissive graphics to an eye of a user and an attenuation display layer for presenting attenuation graphics between the emissive display layer and a real-world scene to block light of the real-world scene from the emissive graphics. A light region compensation module dilates an attenuation graphic based on an attribute of an eye of a viewer, such as size of a pupil, to produce an expanded attenuation graphic that blocks additional light to compensate for an unintended light region. A dark region compensation module camouflages an unintended dark region with a replica graphic in the emissive display layer that reproduces an appearance of the real-world scene in the unintended dark region. A camera provides the light data used to generate the replica graphic.

Replica graphic causing reduced visibility of an image artifact in a direct-view of a real-world scene

An update basis for updating digital content in a digital medium environment is described. The digital content is updated by incorporating new digital content components from a service provider system, such as a stock content service, to keep the digital content from seeming stale to client device users. The service provider system controls provision of digital content components according to an update basis described in a component request. In part, component requests ask that the service provider system provide digital content components for incorporation with digital content. Component requests also describe a timing basis with which digital content components are to be provided as updates. By way of example, the timing basis may correspond to a time interval (e.g., daily, weekly, monthly, seasonally, times of day, and so on), receiving user input in relation to the digital content (e.g., a navigation input to a web page), and so forth.

Update basis for updating digital content in a digital medium environment

Image compensation for an occluding direct-view augmented reality system

An augmented reality display alternates between displaying color frames and alpha frames to generate composite images for transparency control. A display processor includes two sets of buffers, each set including a color frame buffer and an alpha frame buffer. One set of buffers is used to provide data to the display while new video data is being written into the other set of buffers. The display processor switches which set of buffers is providing data and which set of buffers is having new video data written into them. By switching the alpha and color frame buffers in sets, a pair of color frame buffer and alpha frame buffer are always the current set of buffers to provide data as the output. If a frame drop occurs and the next color frame or alpha frame is not ready, the set of buffers is not switched to avoid disturbing flashing visual artifacts.

Controlling an augmented reality display with transparency control using multiple sets of video buffers

Font replacement based on visual similarity is described. In one or more embodiments, a font descriptor includes multiple font features derived from a visual appearance of a font by a font visual similarity model. The font visual similarity model can be trained using a machine learning system that recognizes similarity between visual appearances of two different fonts. A source computing device embeds a font descriptor in a document, which is transmitted to a destination computing device. The destination compares the embedded font descriptor to font descriptors corresponding to local fonts. Based on distances between the embedded and the local font descriptors, at least one matching font descriptor is determined. The local font corresponding to the matching font descriptor is deemed similar to the original font. The destination computing device controls presentations of the document using the similar local font. Computation of font descriptors can be outsourced to a remote location.

Font replacement based on visual similarity

Growing community of inventors

Los Altos, CA, United States of America

Gavin Stuart Peter Miller