An image providing apparatus configured to generate, by using a first artificial intelligence (AI) network, AI metadata including class information and at least one class map, in which the class information includes at least one class corresponding to a type of an object among a plurality of predefined objects included in a first image and the at least one class map indicates a region corresponding to each class in the first image, generate an encoded image by encoding the first image, and output the encoded image and the AI metadata through the output interface.

A processing device and an operating method of the processing device are provided. An embodiment of the present disclosure provides the processing device that obtains a reconstructed image of the raw image by compressing a raw image at a preset compression ratio, encoding the compressed raw image, and decoding the encoded image, recognizes, in the raw image, a target object and a first region of interest (ROI) including the target object and extracts a first feature vector from the target object recognized in the raw image, recognizes, in the reconstructed image, the target object and a second ROI including the target object and extracts a second feature vector from the target object recognized in the reconstructed image, determines whether the target object is recognized in the reconstructed image, based on a degree of overlap between the first and second ROIs and a degree of similarity between the first and second feature vectors, and adjusts the preset compression ratio according to whether the target object is recognized.

Provided are a method, server device, and system for processing offloaded data, the method including receiving the offloaded data from a terminal device, decoding the offloaded data by using a decoder model, and outputting inferred data corresponding to the offloaded data by using a deep neural network model having received the decoded data as an input, wherein the offloaded data includes latent representation data generated by an extractor model having received original data as an input, and the extractor model, the decoder model, and the deep neural network model are jointly trained by using loss information of the deep neural network model.

A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

A method for lossily compressing a sequence of video frames into a representation, wherein each video frame comprises pixels that carry color values. The method includes: segmenting each video frame into superpixels, wherein these superpixels are groups of pixels that share at least one predetermined common property; assigning, to each superpixel in each video frame, at least one attribute derived from the pixels belonging to the respective superpixel; and combining superpixels as nodes in a graph representation, wherein superpixels in a same video frame are connected by spatial edges associated with at least one quantity that is a measure for a distance between these superpixels; and in response to superpixels in adjacent video frames in the sequence meeting at least one predetermined relatedness criterion, these superpixels are connected by temporal edges.

A method of processing image data is provided. Pixel data for a first image is preprocessed to identify a subset of the pixel data corresponding to a region of interest depicting a scene element. The subset of the pixel data is processed at a first encoder to generate a first data structure representative of the region of interest, the first data structure identifying the scene element depicted in the region of interest. The subset of pixel data is also processed at a second encoder to generate a second data structure representative of the region of interest, the second data structure comprising values for visual characteristics associated with the scene element. The first and second data structures are outputted for use by a decoder to generate a second image approximating the region of interest of the first image.

This invention concerns a method of filming a subject to be projected as a Pepper's Ghost image. The method may comprise filming a subject under a lighting arrangement having one or more front lights for illuminating a front of a subject and one or more backlights. The lights may be controlled such that the total brightness of the one or more front lights, as measured of the subject, is less than or approximately the same as the total brightness of the one or more backlights, as measured at the subject. The subject may be located directly above one or more floor lights such the subject is illuminated from below by the one or more floor lights.

This invention concerns a method of filming a subject to be projected as a Pepper's Ghost image. The method may comprise filming a subject under a lighting arrangement having one or more front lights for illuminating a front of a subject and one or more backlights. The lights may be controlled such that the total brightness of the one or more front lights, as measured of the subject, is less than or approximately the same as the total brightness of the one or more backlights, as measured at the subject. The subject may be located directly above one or more floor lights such the subject is illuminated from below by the one or more floor lights.

Methods, systems and computer program products, for producing streams of image frames. Image frames in streaming video are segmented into background segments and instance segments. A background image frame containing the background segments is created. At least some of the instance segments are classified into movable objects of interest and movable objects of non-interest. During a background update time period, the background image frame is updated when a movable object of non-interest has moved to reveal a background area, to include the revealed background area in the background image frame. A foreground image containing the movable objects of interest is created. Blocks of pixels of the updated background and foreground image frames are encoded. A stream of encoded foreground image frames having a first frame rate is produced. A stream of encoded updated background image frames a second, lower frame rate is produced.