Abstract: The subject technology selects a set of augmented reality content generators from available augmented reality content generators, the selected set of augmented reality content generators comprising at least one augmented reality content generator for applying a three-dimensional (3D) effect. The subject technology causes display of a carousel interface including selectable graphical items, each selectable graphical item corresponding to a respective augmented reality content generator. The subject technology receives a selection of a first selectable graphical item from the selectable graphical items, the first selectable graphical item including a first augmented reality content generator for applying a first 3D effect. The subject technology applies, to first image data and first depth data, the first augmented reality content generator corresponding to the selected first selectable graphical item.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for rendering a three-dimensional virtual object in a video clip. The method and system include capturing, using a camera-enabled device, video content of a real-world scene and movement information collected by the camera-enabled device during capture of the video content. The captured video and movement information are stored. The stored captured video content is processed to identify a real-world object in the scene. An interactive augmented reality display is generated that: adds a virtual object to the stored video content to create augmented video content comprising the real-world scene and the virtual object; and adjusts, during playback of the augmented video content, an on-screen position of the virtual object within the augmented video content based at least in part on the stored movement information.

Abstract: Systems and methods are provided for receiving a two-dimensional (2D) image comprising a 2D object; identifying a contour of the 2D object; generating a three-dimensional (3D) mesh based on the contour of the 2D object; and applying a texture of the 2D object to the 3D mesh to output a 3D object representing the 2D object.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and method for performing operations comprising: receiving, by a messaging application, an image generated by a camera of a user; displaying an option to crop an object depicted in the image, determining whether the object is depicted in the image; selectively enabling selection of the option to crop the object based on determining whether the object is depicted in the image; receiving input that selects the option to crop an object depicted in the image when the option is enabled; in response to receiving the input, segmenting the image to separate the object from other portions depicted in the image; extracting the object from the image; and adding the extracted object to a new image as a virtual object.

Abstract: The subject technology receives a selection of a selectable graphical item from a plurality of selectable graphical items, the selectable graphical item comprising an augmented reality content generator for applying a 3D effect, the 3D effect including at least one beautification operation. The subject technology captures image data and depth data using a camera. The subject technology applies, to the image data and the depth data, the 3D effect including the at least one beautification operation based at least in part on the augmented reality content generator, the beautification operation being performed as part of applying the 3D effect. The subject technology generates a 3D message based at least in part on the applied 3D effect including the at least one beautification operation. The subject technology renders a view of the 3D message based at least in part on the applied 3D effect including the at least one beautification operation.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and method for performing operations comprising: receiving, by a messaging application, an image from a camera of a user device; receiving input that selects a user-customizable effects option for activating a user-customizable effects mode; in response to receiving the input, displaying an array of a plurality of effect options together with the image proximate to the user-customizable effects option; and applying a first effect associated with a first effect option of the plurality of effect options to the image.

Abstract: The subject technology generates depth data using a machine learning model based at least in part on captured image data from at least one camera of a client device. The subject technology applies, to the captured image data and the generated depth data, a 3D effect based at least in part on an augmented reality content generator. The subject technology generates a depth map using at least the depth data. The subject technology generates a packed depth map based at least in part on the depth map, the generating the packed depth map. The subject technology converts a single channel floating point texture to a raw depth map. The subject technology generates multiple channels based at least in part on the raw depth map. The subject technology generates a segmentation mask based at least on the captured image data. The subject technology performs background inpainting and blurring of the captured image data using at least the segmentation mask to generate background inpainted image data.

Abstract: Systems, devices, media and methods are presented for presentation of modified objects within a video stream. The systems and methods select an object of interest depicted within a user interface based on an associated image modifier, determine a modifier context based at least in part on one or more characteristics of the selected object, identify a set of image modifiers based on the modifier context, rank a first portion of the identified set of image modifiers based on a primary ordering characteristic, rank a second portion of the identified set of image modifiers based on a secondary ordering characteristic and cause presentation of the modifier icons for the ranked set of image modifiers.

Abstract: The subject technology receives image data and depth data. The subject technology selects an augmented reality content generator corresponding to a three-dimensional (3D) effect. The subject technology applies the 3D effect to the image data and the depth data based at least in part on the selected augmented reality content generator. The subject technology generates, using a processor, a message including information related to the applied 3D effect, the image data, and the depth data.

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can he assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented. using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for rendering three-dimensional virtual objects within real-world environments. Virtual rendering of a three-dimensional virtual object can be altered appropriately as a user moves around the object in the real-world through utilization of a redundant tracking system comprising multiple tracking sub-systems. Virtual object rendering can be with respect to a reference surface in a real-world three-dimensional space depicted in a camera view of a mobile computing device.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for rendering a three-dimensional virtual object in a video clip. The method and system include capturing, using a camera-enabled device, video content of a real-world scene and movement information collected by the camera-enabled device during capture of the video content. The captured video and movement information are stored. The stored captured video content is processed to identify a real-world object in the scene. An interactive augmented reality display is generated that: adds a virtual object to the stored video content to create augmented video content comprising the real-world scene and the virtual object and adjusts, during playback of the augmented video content, an on-screen position of the virtual object within the augmented video content based at least in part on the stored movement information.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for rendering three-dimensional virtual objects within real-world environments. Virtual rendering of a three-dimensional virtual object can be altered appropriately as a user moves around the object in the real-world through utilization of a redundant tracking system comprising multiple tracking sub-systems. Virtual object rendering can be with respect to a reference surface in a real-world three-dimensional space depicted in a camera view of a mobile computing device.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and method for performing operations comprising: receiving, by a messaging application, a video feed from a camera of a user device that depicts a face; receiving a request to add a 3D caption to the video feed; identifying a graphical element that is associated with context of the 3D caption; and displaying the 3D caption and the identified graphical element in the video feed at a position in 3D space of the video feed proximate to the face depicted in the video feed.

Abstract: Systems and methods are provided for receiving a two-dimensional (2D) image comprising a 2D object; identifying a contour of the 2D object; generating a three-dimensional (3D) mesh based on the contour of the 2D object; and applying a texture of the 2D object to the 3D mesh to output a 3D object representing the 2D object.

Abstract: Systems and methods are provided for determining a location of a selection in a space viewable in a camera view on a display of a computing device, detecting movement of the computing device, and generating a path based on the location of the selection and the movement of the computing device. The systems and methods further provide for generating a three-dimensional (3D) mesh along the path, populating the 3D mesh with selected options to generate a 3D paint object, and causing the generated 3D paint object to be displayed. The systems and methods further provide for receiving a request to send a message comprising an image or video overlaid by the 3D paint object, capturing the image or video overlaid by the displayed 3D paint object, generating the message comprising the image or video overlaid by the 3D paint object, and sending the message to another computing device.

Abstract: The subject technology generates depth data using a machine learning model based at least in part on captured image data from at least one camera of a client device. The subject technology applies, to the captured image data and the generated depth data, a 3D effect based at least in part on an augmented reality content generator. The subject technology generates a depth map using at least the depth data. The subject technology generates a packed depth map based at least in part on the depth map, the generating the packed depth map. The subject technology converts a single channel floating point texture to a raw depth map. The subject technology generates multiple channels based at least in part on the raw depth map. The subject technology generates a segmentation mask based at least on the captured image data. The subject technology performs background inpainting and blurring of the captured image data using at least the segmentation mask to generate background inpainted image data.

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for rendering three-dimensional virtual objects within real-world environments. Virtual rendering of a three-dimensional virtual object can be altered appropriately as a user moves around the object in the real-world through utilization of a redundant tracking system comprising multiple tracking sub-systems. Virtual object rendering can be with respect to a reference surface in a real-world three-dimensional space depicted in a camera view of a mobile computing device.