Adobe, Inc.

New York University

Holger Winnemoeller

Wilmot Wei-Mau Li

Jun Xie

Aaron Phillip Hertzmann

Simon Breslav

Jingwan Lu

Baldo Antonio Faieta

Lubomira A Dontcheva

Stephen N Schiller

Shabnam Ghadar

Ratheesh Kalarot

Wilmot Li

Christian Thomas Cantrell

Cameron Smith

Wei-An Lin

Akhilesh Kumar

Wilson Chan

Archie Samuel Bagnall

Patrick James Hebron

Sven Olsen

Jason C Chuang

Alexandrina Orzan

Piotr Walczyszyn

Hijung Shin

Seungyong Lee

Morgan Dixon

Blake Williford

Matthias Trapp

Adrian Joseph Secord

Daniela Cecilia Steinsapir Stitchkin

Yongjin Kim

Jasper O'Leary

Romain Vergne

The present disclosure describes systems, methods, and non-transitory computer readable media for detecting user interactions to edit a digital image from a client device and modify the digital image for the client device by using a web-based intermediary that modifies a latent vector of the digital image and an image modification neural network to generate a modified digital image from the modified latent vector. In response to user interaction to modify a digital image, for instance, the disclosed systems modify a latent vector extracted from the digital image to reflect the requested modification. The disclosed systems further use a latent vector stream renderer (as an intermediary device) to generate an image delta that indicates a difference between the digital image and the modified digital image. The disclosed systems then provide the image delta as part of a digital stream to a client device to quickly render the modified digital image.

Web-based digital image editing in real time utilizing a latent vector stream renderer and an image modification neural network

The present disclosure relates to systems, methods, and non-transitory computer-readable media for using modularized digital editing action blocks in a graphical user interface to generate and apply a variety of advanced modifications to a digital image. The disclosed systems can categorize the digital editing action blocks into digital editing action categories from which a user can select a digital editing action block and insert into a field of a node compositor. Once the digital editing action block is arranged at a compatible field within the digital editing user interface, the snap effects system can execute the digital editing action block to create a particular graphical effect according to the positional configuration of the digital editing action block within the node compositor. In turn, the snap effects system can save the action-block configuration within the node compositor and facilitate additional use and/or sharing thereof.

Utilizing modularized action blocks in a graphical user interface to generate digital images with custom modifications

Introduced here are computer programs and associated computer-implemented techniques for finding the correspondence between sets of graphical elements that share a similar structure. In contrast to conventional approaches, this approach can leverage the similar structure to discover how two sets of graphical elements are related to one another without the relationship needing to be explicitly specified. To accomplish this, a graphics editing platform can employ one or more algorithms designed to encode the structure of graphical elements using a directed graph and then compute element-to-element correspondence between different sets of graphical elements that share a similar structure.

Algorithmic approach to finding correspondence between graphical elements

Techniques of managing design iterations include generating data linking selected snapshot histories with contextual notes within a single presentation environment. A designer may generate a design iteration in a design environment. Once the design iteration is complete, the designer may show a snapshot of the design iteration to a stakeholder. The stakeholder then may provide written contextual notes within the design environment. The computer links the contextual notes to the snapshot and stores the snapshot and contextual notes in a database. When the designer generates a new design iteration from the previous design iteration and the contextual notes, the computer generates a new snapshot and a link to the previous snapshot to form a timeline of snapshots. The designer may then present the snapshots, the timeline, and the contextual notes to the stakeholder as a coherent history of how the design of the mobile app evolved to its present state.

Integrated computing environment for managing and presenting design iterations

In implementations of a color picker, a color picker is generated and exposed in the context of color adjustment, making it easier for a user to select an appropriate color than with full-screen color pickers. A color picker acts as a window into a larger color map by exposing a portion of the color map selectable with touch gestures, enabling a user to easily access any content of a color map having very large numbers of color, at any desired level of detail, and determine a desired color. An indicator of current color at a fixed position of a color picker is updated in real time as content exposed by the color picker is updated. Hence, the current color is determined without obstruction by a user, as opposed to a user touching directly on a color to select a current color.

Color picker

Techniques are disclosed for augmenting an interactive communication session with contextually relevant information. A computing device, such as a smartphone or tablet computer, can be configured to provide an augmented chat application configured to create, send, receive and display a conversation, and further configured to locate, retrieve and display, via a graphical user interface (GUI), other information that is contextually relevant to the conversation. The contextual information may be shared with one or more other users who are participating in the conversation either automatically or in response to a user input. The contextual information can be displayed or otherwise presented to the user explicitly (e.g., the actual content of the contextual information can be displayed via the GUI) or implicitly (e.g., a referent to the contextual information, such as a hyperlink or other cue, can be displayed via the GUI).

Interactive communication augmented with contextual information

Enhanced vectorization of raster images is described. An image vectorization module converts a raster image with bitmapped data to a vector image with vector elements based on mathematical formulas. In some embodiments, spatially-localized control of a vectorization operation is provided to a user. First, the user can adjust an intensity of a denoising operation differently at different areas of the raster image. Second, the user can adjust an automated segmentation by causing one segment to be split into two segments along a zone marked with an indicator tool, such as a brush. Third, the user can adjust an automated segmentation by causing two segments to be merged into a combined segment. The computation of the vector elements is based on the adjusted segmentation. In other embodiments, semantic information gleaned from the raster image is incorporated into the vector image to facilitate manipulation, such as joint selection of multiple vector elements.

Enhanced vectorization of raster images

Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user 'should' draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize 'correctly' drawn lines and de-emphasize &#x201c;incorrectly&#x201d; drawn lines.

Providing drawing assistance using feature detection and semantic labeling

Methods for providing drawing assistance to a user sketching an image include geometrically correcting and parametrically adjusting user strokes to improve their placement and appearance. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a feature of the image the user is intending to draw. To further improve the user strokes, parametric adjustments are made to the geometrically-corrected stroke to emphasize 'correctly' drawn lines and de-emphasize 'incorrectly' drawn lines.

Geometrically and parametrically modifying user input to assist drawing

Methods, apparatus, and computer-readable storage media for stereo drawing that enable the creation of stereoscopic image pairs. A stereo drawing system may present 3D shape(s) via a user interface (UI). The user can position and rotate a 3D shape, for example via direct manipulation technology such as motion tracking technology. A drawing surface may be mapped to an input device via which input strokes may be applied to the surface. The input strokes are mapped locally onto the surface, thereby allowing the user to draw onto a well-defined shape in 3D space. The stereo drawing system maps what is drawn onto the drawing surface; the geometry of the drawing surface provides depth information so that stereoscopic image pairs can be automatically generated.

Methods and apparatus for digital stereo drawing

Methods and apparatus for marker-based stylistic rendering may be used to automatically synthesize the stylistic range of various stylistic rendering techniques. An image processing pipeline may automatically generate stylistic images, such as Hedcut stipple images. Using virtual markers to determine locations in the image to which physical markers are to be attached, the tone of an original source image may be automatically reproduced via placement of stipple dots or other physical markers, while at the same time allowing for stylistic refinement of placement and appearance of the physical markers, e.g. along strong features in the source image.

Methods and apparatus for marker-based stylistic rendering

Methods and apparatus for directional texture generation using image warping. An image warping directional texture generation method may, for example, be used to design hair or hairstyles. The method may obtain one or more user strokes via a provided brush or other user interface element to paint directional texture, such as hair, onto a target image. Primitives, such as strands, wisps, partings, etc., may be used to paint the directional texture. After the user applies a stroke to paint a primitive or a portion of a primitive onto the target image, the primitive may be automatically adjusted to fit the primitive to the stroke, handle distortion artifacts, and blend the primitive into the existing image. The user may continue to apply strokes until satisfied with the overall result.

Growing community of inventors

Seattle, WA, United States of America

Holger Winnemoeller