Adobe, Inc.

Michael Spencer Cragg

Remon Tijssen

Yaniv De Ridder

Yue Shen

Chintan Intwala

Alan Lee Erickson

William Thomas Ruby

Danielle Takara Morimoto

Dana Michelle Jefferson

Davis Taylor Brown

Benjamin Adam Farrell

Colin Cronin Roache

Systems and methods for non-destructive image editing are described. Embodiments are configured to obtain, via a document editor user interface, a selection input identifying a portion of a first image displayed in the document editor user interface. According to some aspects, the first image is part of a first layer of a multilayer document. Embodiments are further configured to: obtain an image generation text prompt; generate, using an image generation network, a second image based on the first image and the image generation text prompt; and present, via a multilayer window of the document editor user interface, a first element representing the first layer of the multilayer document and a second element representing a second layer of the multilayer document. The first element includes the first image and the second element includes the second image and a mask corresponding to the portion of the first image.

Non-destructive generative image editing

In some embodiments, an image processing application executing on a processing device detects an object in an image that is in a field of view of a camera associated with the processing device. The image processing application further determines, based on the object detected in the image, a recommended filter for the image from a list of filters available for filtering the image. The image processing application causes a display device to display a user interface that includes a contextual user interface control. The contextual user interface control indicates that a context-aware image filtering mode is available for the image. Responsive to receiving a selection of the contextual user interface control, the image processing application enables the context-aware image filtering mode by automatically applying the recommended filter to the image to generate a filtered image and causes the display device to display the filtered image.

Context-aware image filtering

Techniques are disclosed for providing guidance information for guiding a user to capture an image according to a predefined composition. A first user may provide information identifying a reference frame that defines a composition desired by the first user. The reference frame depicts a particular view of the real-world environment that the first user desires as the composition of the photo-to-be-taken by a second user. Based upon the reference frame and using augmented reality techniques, AR content is presented to a second user that guides the second user in positioning and orienting the image capture device such that the live view captured by the image capture device matches the particular view. When the live view aligns with the particular view, the second user may take a photo. The composition of such a photo matches the composition desired by the first user and represented by the reference frame.

Virtual frame for guided image composition

Embodiments of the present invention provide systems, methods, and computer storage media for facilitating layout designs. In embodiments, an input event is detected indicating a desire to include a new object within a layout design including a first component. Thereafter, it is determined that the first component within the layout is to be modified to accommodate a second component containing the new object. The layout design is automatically modified to include the first component and the second component in the layout design.

Dynamic layout design

Techniques and systems to support immersive media content navigation and editing are described. A two-dimensional equirectangular projection of a spherical video is generated by a computing device and displayed in a navigator portion of a user interface of a content editing application. A visual position indicator, indicative of a position within the spherical video, is displayed over the 2D equirectangular projection of the spherical video. A portion of the spherical video is determined based on the position, and a planar spherical view of the portion of the spherical video is generated by the computing device and displayed in a compositor portion of the user interface. The navigator portion and the compositor portion are linked such that user input to the navigator portion or the compositor portion of the user interface causes corresponding visual changes in both the navigator portion and the compositor portion of the user interface.

Immersive media content navigation and editing techniques

Embodiments of the present invention provide systems, methods, and computer storage media for facilitating synchronization of audio with motion imagery. In embodiments, an indication to create a relationship between an audio feature associated with an audio and an imagery feature associated with a motion imagery is received. Thereafter, a relationship is created between the audio feature and the imagery feature in accordance with an instance or a time duration to synchronize the audio with the motion imagery. Based on the relationship between the audio feature and the imagery feature, the imagery feature of the component is automatically manipulated in relation to the audio feature at the designated instance or the time duration.

Facilitating synchronization of motion imagery and audio

In embodiments of physics-based cell layout redesign, a computing device displays a cell layout interface that includes cells in a cell grid, and the computing device implements a physics-based algorithm as a computer application that can receive a redesign input to manipulate a cell in the cell layout interface. The physics-based algorithm is implemented to then determine one or more of the cells that are proximate the manipulated cell based on edge relations between an edge of the manipulated cell and respective edges of the one or more cells. The physics-based algorithm can then reconfigure the one or more proximate cells based on the redesign input to the manipulated cell and the edge relations between the edges of the cells.

Growing community of inventors

Berkeley, CA, United States of America

Michael Spencer Cragg