A macro block size determining unit 1 determines the size of each macro block on a frame-by-frame basis. A macro block dividing unit 2 divides an inputted image into macro blocks each having the size determined by the macro block size determining unit 1. A macro block coding unit 3 determines a coding mode for each of the macro blocks divided by the macro block dividing unit 2, and codes pixel values in each of the macro blocks in the determined coding mode.

An encoding apparatus, includes a memory; and a processor coupled to the memory and configured to: perform intra-screen prediction encoding on an image of a region of a still image cut out from a first decoded image corresponding to a screen image before a predetermined region is switched from a video to a still image, generate a second decoded image obtained by decoding information for which the intra-screen prediction is performed, and when a first screen image after the predetermined region is switched from a video to a still image is received, perform inter-screen prediction encoding on an image of a region of a still image cut out from the first screen image after switching to a still image, by referring to the generated second decoded image.

An encoding apparatus, includes a memory; and a processor coupled to the memory and configured to: perform intra-screen prediction encoding on an image of a region of a still image cut out from a first decoded image corresponding to a screen image before a predetermined region is switched from a video to a still image, generate a second decoded image obtained by decoding information for which the intra-screen prediction is performed, and when a first screen image after the predetermined region is switched from a video to a still image is received, perform inter-screen prediction encoding on an image of a region of a still image cut out from the first screen image after switching to a still image, by referring to the generated second decoded image.

At least a method and an apparatus are presented for efficiently encoding or decoding video. For example, a plurality of frames is provided to a motion estimator to produce an output comprising estimated motion information. The estimated motion information is provided to an auto-encoder or an auto-decoder to produce an output comprising reconstructed motion field. The reconstructed motion field and one or more decoded frames of the plurality of frames are provided to a deep neural network to produce an output comprising refined bi-directional motion field. The video is encoded or decoded based on the refined bi-directional motion field.

At least a method and an apparatus are presented for efficiently encoding or decoding video. For example, a plurality of frames is provided to a motion estimator to produce an output comprising estimated motion information. The estimated motion information is provided to an auto-encoder or an auto-decoder to produce an output comprising reconstructed motion field. The reconstructed motion field and one or more decoded frames of the plurality of frames are provided to a deep neural network to produce an output comprising refined bi-directional motion field. The video is encoded or decoded based on the refined bi-directional motion field.

In a multi-person pose recognition method, a to-be-recognized image is obtained, and a circuitous pyramid network is constructed. The circuitous network pyramid includes parallel phases, and each phase includes downsampling network layers, upsampling network layers, and a first residual connection layer to connect the downsampling and upsampling network layers. The phases are interconnected by a second residual connection layer. The circuitous pyramid network is traversed, by extracting a feature map for each phase, and the feature map of the last phase is determined to be the feature map of the to-be-recognized image. Multi-pose recognition is then performed on the to-be-recognized image according to the feature map to obtain a pose recognition result for the to-be-recognized image.

In a multi-person pose recognition method, a to-be-recognized image is obtained, and a circuitous pyramid network is constructed. The circuitous network pyramid includes parallel phases, and each phase includes downsampling network layers, upsampling network layers, and a first residual connection layer to connect the downsampling and upsampling network layers. The phases are interconnected by a second residual connection layer. The circuitous pyramid network is traversed, by extracting a feature map for each phase, and the feature map of the last phase is determined to be the feature map of the to-be-recognized image. Multi-pose recognition is then performed on the to-be-recognized image according to the feature map to obtain a pose recognition result for the to-be-recognized image.

A method of motion compensation for geometry representation of 3D data is described herein. The method performs motion compensation by first identifying correspondent 3D surfaces in time domain, then followed by a 3D to 2D projection of motion compensated 3D surface patches, and then finally performing 2D motion compensation on the projected 3D surface patches.

A method of motion compensation for geometry representation of 3D data is described herein. The method performs motion compensation by first identifying correspondent 3D surfaces in time domain, then followed by a 3D to 2D projection of motion compensated 3D surface patches, and then finally performing 2D motion compensation on the projected 3D surface patches.

A device for recognizing a motion in a vehicle according to an embodiment of the present disclosure may include a camera for acquiring a user image, and a controller that divides the user image into a first region, a second region, and a third region in which the first region and the second region overlap each other, and recognizes a motion of a user occurring in at least one of the first region, the second region, or the third region.