Abstract: The present disclosure describes techniques of generating voices for virtual characters. A plurality of source sounds may be received. The plurality of source sounds may correspond to a plurality of frames of a video. The video may comprise a virtual character. The plurality of source sounds may be converted into a plurality of representations in a latent space using a first model. Each representation among the plurality of representations may comprise a plurality of parameters. The plurality of parameters may correspond to a plurality of sound features. A plurality of sounds may be generated in real time for the virtual character in the video based at least in part on modifying at least one of the plurality of parameters of each representation.

Abstract: An augmented reality-based display method and device, and a storage medium are provided. The method obtains a target object image by performing object segmentation on a target object in a real-time scene image captured by an image acquisition unit; generates a virtual image corresponding to the target object based on the target object image; and displays the virtual image in the real-time scene image based on an augmented reality display technology. By obtaining the target object image, generating the virtual image corresponding to the target object based on the target object image, and displaying the virtual image in the real-time scene image based on an augmented reality (AR) technology, various virtual images can be generated according to user demands to meet the diverse needs of the user and improve the use experience of the user using the AR technology.

Abstract: Systems and methods directed to placing content are described. More specifically, content is received and depth information corresponding to an external environment of the computing device is obtained. An indication to associate the content with a location based on the depth information is received from a user. Information for at least one plane associated with the depth information at the location is obtained and at least a portion of the content is warped to match the at least one plane based on the depth information.

Abstract: An augmented reality-based display method and device, and a storage medium are provided. The method obtains a target object image by performing object segmentation on a target object in a real-time scene image captured by an image acquisition unit; generates a virtual image corresponding to the target object based on the target object image; and displays the virtual image in the real-time scene image based on an augmented reality display technology. By obtaining the target object image, generating the virtual image corresponding to the target object based on the target object image, and displaying the virtual image in the real-time scene image based on an augmented reality (AR) technology, various virtual images can be generated according to user demands to meet the diverse needs of the user and improve the use experience of the user using the AR technology.