Adobe, Inc.

John Nelson

Oliver Wang

Geoffrey Oxholm

Elya Shechtman

Brian Lynn Price

Matthew David Fisher

Lubomira A Dontcheva

Joel Richard Brandt

Li-Yi Wei

Joon-Young Lee

Hijung Shin

Seth John Walker

Dingzeyu Li

Kim Pascal Pimmel

Wilmot Li

Stephen Diverdi

Deepali Aneja

Wenqi Xian

Seoung Wug Oh

Ramiz Sheikh

Wujun Wang

Adam Pikielny

Rubaiat Habib

Jiaju Ma

One or more processing devices access a scene depicting a reference object that includes an annotation identifying a target region to be modified in one or more video frames. The one or more processing devices determine that a target pixel corresponds to a sub-region within the target region that includes hallucinated content. The one or more processing devices determine gradient constraints using gradient values of neighboring pixels in the hallucinated content, the neighboring pixels being adjacent to the target pixel and corresponding to four cardinal directions. The one or more processing devices update color data of the target pixel subject to the determined gradient constraints.

Corrective lighting for video inpainting

Embodiments of the present disclosure provide, a method, a system, and a computer storage media that provide mechanisms for multimedia effect addition and editing support for text-based video editing tools. The method includes generating a user interface (UI) displaying a transcript of an audio track of a video and receiving, via the UI, input identifying selection of a text segment from the transcript. The method also includes in response to receiving, via the UI, input identifying selection of a particular type of text stylization or layout for application to the text segment. The method further includes identifying a video effect corresponding to the particular type of text stylization or layout, applying the video effect to a video segment corresponding to the text segment, and applying the particular type of text stylization or layout to the text segment to visually represent the video effect in the transcript.

Video editing using transcript text stylization and layout

Embodiments are disclosed for a machine learning-based chroma keying process. The method may include receiving an input including an image depicting a chroma key scene and a color value corresponding to a background color of the image. The method may further include generating a preprocessed image by concatenating the image and the color value. The method may further include providing the preprocessed image to a trained neural network. The method may further include generating, using the trained neural network, an alpha matte representation of the image based on the preprocessed image.

Machine learning-based chroma keying process

Certain aspects involve video inpainting in which content is propagated from a user-provided reference video frame to other video frames depicting a scene. One example method includes one or more processing devices that performs operations that include accessing a scene depicting a reference object that includes an annotation identifying a target region to be modified in one or more video frames. The operations also includes computing a target motion of a target pixel that is subject to a motion constraint. The motion constraint is based on a three-dimensional model of the reference object. Further, operations include determining color data of the target pixel to correspond to the target motion. The color data includes a color value and a gradient. Operations also include determining gradient constraints using gradient values of neighbor pixels. Additionally, the processing devices updates the color data of the target pixel subject to the gradient constraints.

Certain aspects involve video inpainting in which content is propagated from a user-provided reference frame to other video frames depicting a scene. For example, a computing system accesses a set of video frames with annotations identifying a target region to be modified. The computing system determines a motion of the target region's boundary across the set of video frames, and also interpolates pixel motion within the target region across the set of video frames. The computing system also inserts, responsive to user input, a reference frame into the set of video frames. The reference frame can include reference color data from a user-specified modification to the target region. The computing system can use the reference color data and the interpolated motion to update color data in the target region across set of video frames.

Video inpainting via machine-learning models with motion constraints

Video inpainting via user-provided reference frame

A content and proximity based window layout optimizer is described, including receiving a request to adjust one or more windows in a user interface, the one or more windows having content, determining an adjustment order based on the request, the adjustment order comprising a sequence of the one or more windows on which the request to adjust is applied successively, adjusting the one or more windows based on the request, the adjustment order, and the content of the one or more windows being adjusted.

Content and proximity based window layout optimization

Systems, methods, and computer readable media for editing controls for spatial deformations are described. One embodiment includes a method including the steps of causing an image having at least one unmodified object to be displayed in a window, receiving a deformation of the unmodified object, generating a deformed object based at least in part on the deformation and the unmodified object, and causing the deformed object to be displayed in the window. The method further includes the steps of causing a representation of the unmodified object to be displayed in the window with the deformed object, receiving a selection of a point within the representation of the unmodified object, receiving a modification of a first parameter associated with the unmodified object at the point, regenerating the deformed object based at least in part on the deformation, the unmodified object, and the modified first parameter, and causing the regenerated deformed object to be displayed in the window.

Editing control for spatial deformations

Briefly, in accordance with one or more embodiments, a transparent overlay of available dropzones may be displayed to assist a user in determining a new configuration for a document utilizing drag and drop.

Transparent overlays for predictive interface drag and drop

Growing community of inventors

Normandy Park, WA, United States of America

John Nelson