단일 동영상의 입체 영상으로의 변환

Abstract

The last few years have seen a dramatic increase in the demand for stereo content. This has largely been driven by the commercial availability of multiviewer auto-stereoscopic displays. Such displays require a number of adjacent views of scene. This proposal can help generating stereoscopic video by making the left and right video corresponding two eyes. We propose a method for converting monotonic video to stereoscopic video. The proposed methodology is composed of four major steps. First, given a current video frame, we estimate a motion vector for each block by a conventional block matching motion estimation algorithm. The motion vector is composed of horizontal and vertical disparities. Second, the norm of the motion vector is computed for each block. Due to the reduction of noise, a median filter is performed on the norm of the motion vector in order to enhance the reliability. Third, each block is shifted to the horizontal direction by the norm of the motion vector which is transformed - vi - to binocular parallax. The shift of blocks in the horizontal direction eliminates the effects of the vertical disparity. Finally, all the shifted blocks are synthesized and a synthesized image is then generated. A stereoscopic image pair being composed of the original image and its associated synthesized image is produced. With proper 3-D viewing devices, users can feel 3-D depth from seeing the stereoscopic video.