Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables (“LUTs”).

Abstract: The present disclosure provides systems and methods for image editing. Embodiments of the present disclosure provide an image editing system for perform image object replacement or image region replacement (e.g., an image editing system for replacing an object or region of an image with an object or region from another image). For example, the image editing system may replace a sky portion of an image with a more desirable sky portion from a different replacement image. The original image and the replacement image (e.g., the image including a desirable object or region) include layers of masks. A sky from the replacement image may replace the sky of the image to produce an aesthetically pleasing composite image.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for determining whether a derived attribute from a request is stored at a derived attribute cache. In particular, in one or more embodiments, the disclosed systems obtain the derived attribute from artificial-intelligence models if the derived attribute is unavailable at the derived attribute cache. If the derived attribute is available at the derived attribute cache, the disclosed system returns the derived attribute in response to a request without having the artificial-intelligence models rederive the attribute.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate preliminary object masks for objects in an image, surface the preliminary object masks as object mask previews, and on-demand converts preliminary object masks into refined object masks. Indeed, in one or more implementations, an object mask preview and on-demand generation system automatically detects objects in an image. For the detected objects, the object mask preview and on-demand generation system generates preliminary object masks for the detected objects of a first lower resolution. The object mask preview and on-demand generation system surfaces a given preliminary object mask in response to detecting a first input. The object mask preview and on-demand generation system also generates a refined object mask of a second higher resolution in response to detecting a second input.

Abstract: The present disclosure provides systems and methods for image editing. Embodiments of the present disclosure provide an image editing system for perform image object replacement or image region replacement (e.g., an image editing system for replacing an object or region of an image with an object or region from another image). For example, the image editing system may replace a sky portion of an image with a more desirable sky portion from a different replacement image. The original image and the replacement image (e.g., the image including a desirable object or region) include layers of masks. A sky from the replacement image may replace the sky of the image to produce an aesthetically pleasing composite image.

Abstract: The present disclosure provides systems and methods for image editing. Embodiments of the present disclosure provide an image editing system for perform image object replacement or image region replacement (e.g., an image editing system for replacing an object or region of an image with an object or region from another image). For example, the image editing system may replace a sky portion of an image with a more desirable sky portion from a different replacement image. The original image and the replacement image (e.g., the image including a desirable object or region) include layers of masks. A sky from the replacement image may replace the sky of the image to produce an aesthetically pleasing composite image.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables (“LUTs”).

Abstract: This application relates generally to modifying visual data based on audio commands and more specifically, to performing complex operations that modify visual data based on one or more audio commands. In some embodiments, a computer system may receive an audio input and identify an audio command based on the audio input. The audio command may be mapped to one or more operations capable of being performed by a multimedia editing application. The computer system may perform the one or more operations to edit to received multimedia data.

Abstract: This application relates generally to modifying visual data based on audio commands and more specifically, to performing complex operations that modify visual data based on one or more audio commands. In some embodiments, a computer system may receive an audio input and identify an audio command based on the audio input. The audio command may be mapped to one or more operations capable of being performed by a multimedia editing application. The computer system may perform the one or more operations to edit to received multimedia data.

Abstract: A mesh is a collection of multiple shapes referred to as elements, each of which can share an edge with one or more other elements of the mesh. The mesh is presented to the user on a display, and the user identifies a new element to be added to the mesh. User input is received to manipulate the new element (e.g., move the new element around the display). As the new element is manipulated, various conditions are applied to determine edges of elements existing in the mesh that the new element can be snapped to. Snapping a new element to an edge of an existing element in the mesh refers to adding the new element to the mesh so that the new element and the existing element share the edge. Indications of the edges of existing elements to which the new element can be snapped are provided to the user.

Abstract: The present disclosure is directed toward systems and methods for generating an interactive digital media item based on a two-dimensional “selfie.” For example, one or more embodiments described herein identifies a face in the two-dimensional “selfie,” then builds and displays a three-dimensional model based on the identified face. One or more embodiments described herein also track movement of a viewer of a computing device displaying the three-dimensional model such that one or more portions of the three-dimensional model appear to follow the person viewing the “selfie.

Abstract: The present disclosure is directed toward systems and methods for generating an interactive digital media item based on a two-dimensional “selfie.” For example, one or more embodiments described herein identifies a face in the two-dimensional “selfie,” then builds and displays a three-dimensional model based on the identified face. One or more embodiments described herein also track movement of a viewer of a computing device displaying the three-dimensional model such that one or more portions of the three-dimensional model appear to follow the person viewing the “selfie.

Abstract: A mesh is a collection of multiple shapes referred to as elements, each of which can share an edge with one or more other elements of the mesh. The mesh is presented to the user on a display, and the user identifies a new element to be added to the mesh. User input is received to manipulate the new element (e.g., move the new element around the display). As the new element is manipulated, various conditions are applied to determine edges of elements existing in the mesh that the new element can be snapped to. Snapping a new element to an edge of an existing element in the mesh refers to adding the new element to the mesh so that the new element and the existing element share the edge. Indications of the edges of existing elements to which the new element can be snapped are provided to the user.

Abstract: Automated sharing of digital images is described. In example implementations, a computing device, such as a smart phone, captures a digital image depicting multiple faces of multiple persons included in the digital image. The computing device is capable of automatically distributing a copy of the digital image to the subjects of the digital image. To do so, a digital image sharing module determines a person identifier using facial detection and recognition. The person identifier, which can be derived from facial characteristics, is used to search a contact information database and find a matching entry. The matching entry includes contact information associated with the person in the digital image. The sharing module transmits a copy of the digital image to the person using the contact information. The digital image sharing module can also display a sharing status indicator indicative of whether the digital image can be, or has been, transmitted automatically.

Abstract: A mesh is a collection of multiple shapes referred to as elements, each of which can share an edge with one or more other elements of the mesh. The mesh is presented to the user on a display, and the user identifies a new element to be added to the mesh. User input is received to manipulate the new element (e.g., move the new element around the display). As the new element is manipulated, various conditions are applied to determine edges of elements existing in the mesh that the new element can be snapped to. Snapping a new element to an edge of an existing element in the mesh refers to adding the new element to the mesh so that the new element and the existing element share the edge. Indications of the edges of existing elements to which the new element can be snapped are provided to the user.

Abstract: Automated sharing of digital images is described. In example implementations, a computing device, such as a smart phone, captures a digital image depicting multiple faces of multiple persons included in the digital image. The computing device is capable of automatically distributing a copy of the digital image to the subjects of the digital image. To do so, a digital image sharing module determines a person identifier using facial detection and recognition. The person identifier, which can be derived from facial characteristics, is used to search a contact information database and find a matching entry. The matching entry includes contact information associated with the person in the digital image. The sharing module transmits a copy of the digital image to the person using the contact information. The digital image sharing module can also display a sharing status indicator indicative of whether the digital image can be, or has been, transmitted automatically.

Abstract: Dynamic motion path blur techniques are described. In one or more implementations, paths may be specified to constrain a motion blur effect to be applied to a single image. A variety of different techniques may be employed as part of the motion blur effects, including use of curved blur kernel shapes, use of a mesh representation of blur kernel parameter fields to support real time output of the motion blur effect to an image, use of flash effects, blur kernel positioning to support centered or directional blurring, tapered exposure modeling, and null paths.

Abstract: Dynamic motion path blur techniques are described. In one or more implementations, paths may be specified to constrain a motion blur effect to be applied to a single image. A variety of different techniques may be employed as part of the motion blur effects, including use of curved blur kernel shapes, use of a mesh representation of blur kernel parameter fields to support real time output of the motion blur effect to an image, use of flash effects, blur kernel positioning to support centered or directional blurring, tapered exposure modeling, and null paths.

Abstract: Methods and apparatus for manipulating digital images. A warping module is described that enables the manipulation of a surface by selectively deforming portions of the surface while maintaining local rigidity. The user may position multiple control points on a surface to constrain deformation. The user may specify multiple properties (e.g., translation, rotation, depth, and scale) at each control point. A mesh may be overlaid on the surface. The warping module may perform an initialization in which the properties are propagated other vertices in the mesh to generate an initial deformed mesh. The warping module may then perform an iterative optimization operation on the deformed mesh to improve the deformation while retaining local rigidity. Thus, instead of moving every pixel in the surface, the warping module moves or adjusts coordinates of the vertices of the mesh. The surface is then deformed according to the deformed mesh.

Abstract: Dynamic motion path blur techniques are described. In one or more implementations, paths may be specified to constrain a motion blur effect to be applied to a single image. A variety of different techniques may be employed as part of the motion blur effects, including use of curved blur kernel shapes, use of a mesh representation of blur kernel parameter fields to support real time output of the motion blur effect to an image, use of flash effects, blur kernel positioning to support centered or directional blurring, tapered exposure modeling, and null paths.