Issue No. 07 - July (2012 vol. 18)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2011.114
Jizhou Gao , Center for Visualization & Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
Miao Liao , Center for Visualization & Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
Ruigang Yang , Center for Visualization & Virtual Environments, Univ. of Kentucky, Lexington, KY, USA
Minglun Gong , Dept. of Comput. Sci., Memorial Univ. of Newfoundland, St. John's, NL, Canada
We present a semiautomatic system that converts conventional videos into stereoscopic videos by combining motion analysis with user interaction, aiming to transfer as much as possible labeling work from the user to the computer. In addition to the widely used structure from motion (SFM) techniques, we develop two new methods that analyze the optical flow to provide additional qualitative depth constraints. They remove the camera movement restriction imposed by SFM so that general motions can be used in scene depth estimation-the central problem in mono-to-stereo conversion. With these algorithms, the user's labeling task is significantly simplified. We further developed a quadratic programming approach to incorporate both quantitative depth and qualitative depth (such as these from user scribbling) to recover dense depth maps for all frames, from which stereoscopic view can be synthesized. In addition to visual results, we present user study results showing that our approach is more intuitive and less labor intensive, while producing 3D effect comparable to that from current state-of-the-art interactive algorithms.
video signal processing, image motion analysis, image sensors, image sequences, interactive systems, quadratic programming, stereo image processing, user interfaces, interactive algorithms, video stereolization, motion analysis, user interaction, semiautomatic system, stereoscopic videos, structure-from-motion techniques, SFM techniques, optical flow analysis, qualitative depth constraints, camera movement restriction, scene depth estimation, mono-to-stereo conversion, user labeling task, quadratic programming, quantitative depth, user scribbling, 3D effect, Three dimensional displays, Cameras, Pixel, Labeling, Quadratic programming, Image segmentation, Image sequences, user labeling., Semiautomatic 2D-3D conversion, stereo/3D video/movie, motion analysis
Jizhou Gao, Miao Liao, Ruigang Yang and Minglun Gong, "Video Stereolization: Combining Motion Analysis with User Interaction," in IEEE Transactions on Visualization & Computer Graphics, vol. 18, no. , pp. 1079-1088, 2012.