摘要:
A method of processing image data includes detecting a contour between an occlusion region and a non-occlusion region in a motion vector field of input video, generating a first contour and a second contour from the detected contour based on motion vectors of blocks corresponding to the detected contour, and separating the occlusion region into a first occlusion region adjacent to the first contour and a second occlusion region adjacent to the second contour. The method further includes reconstructing motion vectors of the first occlusion region based on motion vectors of the first contour and reconstructing motion vectors of the second occlusion region based on motion vectors of the second contour.
摘要:
A multi core graphic processing device includes a first graphic core that processes a first segment of a graphic frame divided into a plurality of segments and generates a first local decision that defines a scene property of the first segment, a second graphic core that processes a second segment of the graphic frame different from the first segment and generates a second local decision that defines a scene property of the second segment, and a global decision unit that receives the first local decision and the second local decision from the first graphic core and the second graphic core, and selects one of the received first local decision and second local decision as a global decision.