Abstract: Methods and systems are disclosed for performing operations for transferring garments from one real-world object to another in real time. The operations comprise receiving a first video that includes a depiction of a first person wearing a first upper-body garment in a first pose and obtaining a second video that includes a depiction of a second person wearing a second upper-body garment in a second pose. A pose of the second person depicted in the second video is modified to match the first pose of the first person depicted in the first video. The operations comprise generating an upper-body segmentation of the second upper-body garment which the second person is wearing in the second video in the modified pose and replacing the first upper-body garment worn by the first person in the first video with the second upper-body garment based on the upper-body segmentation.

Abstract: Aspects of the present disclosure involve a system for presenting AR items. The system performs operations including receiving a video that includes a depiction of one or more real-world objects in a real-world environment and obtaining depth data related to the real-world environment. The operations include generating a three-dimensional (3D) model of the real-world environment based on the video and the depth data and adding an augmented reality (AR) item to the video based on the 3D model of the real-world environment. The operations include determining that the AR item has been placed on a vertical plane of the real-world environment and modifying an orientation of the AR item to correspond to an orientation of the vertical plane.

Abstract: A messaging system performs virtual clothing try-on. A method of virtual clothing try-on may include accessing a target garment image and a person image of a person wearing a source garment and processing the person image to generate a source garment mask and a person mask. The method may further include processing the source garment mask, the person mask, the target garment image, and a target garment mask to generate a warping, the warping indicating a warping to apply to the target garment image. The method may further include processing the target garment to warp the target garment in accordance with the warping to generate a warped target garment image, processing the warped target garment image to blend with the person image to generate a person with a blended target garment image, and processing the person with blended target garment image to fill in holes to generate an output image.

Abstract: Aspects of the present disclosure involve a system for providing AR experiences. The system accesses, by a messaging application, an image depicting a real-world fashion item of a user and generates a three-dimensional (3D) virtual fashion item based on the real-world fashion item depicted in the image. The system stores the 3D virtual fashion item in a database that includes a virtual wardrobe comprising a plurality of 3D virtual fashion items associated with the user. The system generates, by the messaging application, an augmented reality (AR) experience that allows the user to interact with the virtual wardrobe.

Abstract: Aspects of the present disclosure involve a system for presenting augmented reality (AR) items. The system performs operations including receiving a video that includes a depiction of a real-world environment and generating a 3D model of the real-world environment based on the video. The operations include determining, based on the 3D model of the real-world environment, that an AR item has been placed in the video at a particular 3D position and identifying a portion of the 3D model corresponding to the real-world environment currently being displayed on a screen. The operations include determining that the 3D position of the AR item is excluded from the portion of the 3D model currently being displayed on the screen and in response, displaying an indicator that identifies the 3D position of the AR item in the 3D model relative to the portion of the 3D model currently being displayed on a screen.

Abstract: Methods and systems are disclosed for performing operations for transferring garments from one real-world object to another in real time. The operations comprise receiving a first video that includes a depiction of a first person wearing a first upper-body garment in a first pose and obtaining a second video that includes a depiction of a second person wearing a second upper-body garment in a second pose. A pose of the second person depicted in the second video is modified to match the first pose of the first person depicted in the first video. The operations comprise generating an upper-body segmentation of the second upper-body garment which the second person is wearing in the second video in the modified pose and replacing the first upper-body garment worn by the first person in the first video with the second upper-body garment based on the upper-body segmentation.

Abstract: Aspects of the present disclosure involve a system for providing virtual experiences. The system accesses, by a messaging application, an image depicting a person. The system generates, by the messaging application, a three-dimensional (3D) avatar based on the person depicted in the image. The system receives input that selects a pose for the 3D avatar and one or more fashion items to be worn by the 3D avatar and places, by the messaging application, the 3D avatar in the selected pose and wearing the one or more fashion items in an augmented reality (AR) experience.

Abstract: Aspects of the present disclosure involve a system for providing virtual experiences. The system accesses an image depicting a person and one or more camera parameters representing a viewpoint associated with a camera used to capture the image. The system extracts a portion of the image comprising the depiction of the person. The system processes, by a neural radiance field (NeRF) machine learning model, the one or more camera parameters to render an estimated depiction of a scene from the viewpoint associated with the camera used to capture the image. The system combines the portion of the image comprising the depiction of the person with the estimated depiction of the scene to generate an output image and causes the output image to be presented on a client device.

Abstract: Aspects of the present disclosure involve a system for providing virtual experiences. The system performs operations including selecting, by a messaging application, a virtual experience that represents a previously captured real-world environment at a first location; accessing an image representing a new real-world environment at a second location, the image depicting a plurality of real-world objects; receiving input that selects a first real-world object from the plurality of real-world objects depicted in the image; and modifying the image, accessed at the second location, based on the virtual experience to depict the previously captured real-world environment with the first real-world object.

Abstract: A messaging system performs virtual clothing try-on. A method of virtual clothing try-on may include accessing a target garment image and a person image of a person wearing a source garment and processing the person image to generate a source garment mask and a person mask. The method may further include processing the source garment mask, the person mask, the target garment image, and a target garment mask to generate a warping, the warping indicating a warping to apply to the target garment image. The method may further include processing the target garment to warp the target garment in accordance with the warping to generate a warped target garment image, processing the warped target garment image to blend with the person image to generate a person with a blended target garment image, and processing the person with blended target garment image to fill in holes to generate an output 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 performing operations comprising: receiving, by a client device associated with a first user, a communication from a second user; retrieving, from the communication, a movement vector representing three-dimensional (3D) movement of a set of skeletal joints of the second user; receiving, by the client device associated with the first user, input that selects a 3D avatar; and animating, based on the movement vector, the 3D avatar to mimic the 3D movement of the set of skeletal joints of the second user.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for performing operations comprising: receiving a video that depicts a person; identifying a set of skeletal joints corresponding to limbs of the person; tracking 3D movement of the set of skeletal joints corresponding to the limbs of the person in the video; causing display of a 3D virtual object that has a plurality of limbs including one or more extra limbs than the limbs of the person in the video; and moving the one or more extra limbs of the 3D virtual object based on the movement of the set of skeletal joints corresponding to the limbs of the person in the video.

Abstract: Embodiments of the present disclosure relate generally to systems for enhancing a first media item through the addition of a supplemental second media item. A user may provide a request to enhance a selected media item, and in response, an enhancement system retrieves and presents a curated collection of supplemental content to be added to the media, to the user. The user may review the curated collection of supplemental content, for example by providing a tactile input to scroll through the curated collection of content.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for performing operations comprising: receiving, by a client device associated with a first user, a communication from a second user; retrieving, from the communication, a movement vector representing three-dimensional (3D) movement of a set of skeletal joints of the second user; receiving, by the client device associated with the first user, input that selects a 3D avatar; and animating, based on the movement vector, the 3D avatar to mimic the 3D movement of the set of skeletal joints of the second user.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for performing operations comprising: receiving a video that depicts a person; identifying a set of skeletal joints corresponding to limbs of the person; tracking 3D movement of the set of skeletal joints corresponding to the limbs of the person in the video; causing display of a 3D virtual object that has a plurality of limbs including one or more extra limbs than the limbs of the person in the video; and moving the one or more extra limbs of the 3D virtual object based on the movement of the set of skeletal joints corresponding to the limbs of the person in the video.

Abstract: Methods and systems are disclosed for performing operations for segmenting an object. The operations include receiving an image that includes a depiction of a first object; receiving a first segmentation dataset; applying a first machine learning technique to the first segmentation dataset and the image to estimate a first segmentation of the first object depicted in the image; generating a second segmentation dataset that includes the estimated first segmentation and a correction to the estimated first segmentation of the first object; applying the first machine learning technique to the second segmentation dataset and the image to estimate a second segmentation of the first object depicted in the image; and applying an augmented reality experience to the image based on the estimated second segmentation of the first object.

Abstract: Aspects of the present disclosure involve a system for presenting AR items. The system performs operations including receiving a video that includes a depiction of one or more real-world objects in a real-world environment and obtaining depth information related to the real-world environment; and generating a 3D model of the real-world environment. The operations further include determining 3D placement and orientation for an AR item based on data associated with the AR item and the 3D model of the real-world environment and causing display of a marker in the video that specifies the 3D placement and orientation of the AR item. The operations further include rendering a display of the AR item within the video according to the 3D placement and orientation in response to movement of the marker within the video.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for performing operations comprising: receiving a video that includes a depiction of a real-world object in a real-world environment; determining a classification for the real-world environment by processing the real-world object depicted in the video; selecting an augmented reality (AR) item based on the classification of the real-world environment and the real-world object depicted in the video; modifying pixels corresponding to the real-world object depicted in the video to generate a modified video that excludes the depiction of the real-world object; and adding the AR item to the modified video at a display position corresponding to the modified pixels.

Abstract: Methods and systems are disclosed for performing operations for transferring motion from one real-world object to another in real-time. The operations comprise receiving a first video that includes a depiction of a first real-world object and extracting an appearance of the first real-world object from the video. The operations comprise obtaining a second video that includes a depiction of a second real-world object and extracting motion of the second real-world object from the second video. The operations comprise applying the motion of the second real-world object extracted from the second video to the appearance of the first real-world object extracted from the first video. The operations comprise generating a third video that includes a depiction of the first real-world object having the appearance of the first real-world object and the motion of the second real-world object.

Abstract: Methods and systems are disclosed for performing operations for transferring garments from one real-world object to another in real time. The operations comprise receiving a first video that includes a depiction of a first person wearing a first upper-body garment in a first pose and obtaining a second video that includes a depiction of a second person wearing a second upper-body garment in a second pose. A pose of the second person depicted in the second video is modified to match the first pose of the first person depicted in the first video. The operations comprise generating an upper-body segmentation of the second upper-body garment which the second person is wearing in the second video in the modified pose and replacing the first upper-body garment worn by the first person in the first video with the second upper-body garment based on the upper-body segmentation.