Complexity-adaptive 2d-to-3d video sequence conversion
作者： Sharath Manjunath , Haohong Wang , Hsiang-Tsun Li
DOI:
关键词: Frame (networking) 、 Artificial intelligence 、 Mathematics 、 Depth map 、 Computer vision 、 2D to 3D conversion 、 Video sequence 、 Stereo image 、 Class (biology) 、 Image processing 、 Image (mathematics)
摘要: Techniques for complexity-adaptive and automatic two-dimensional (2D) to three-dimensional (3D) image video conversion which classifies a frame of 2D input into one flat class non-flat are described. The is directly converted 3D stereo display. that classified as further processed automatically adaptively, based on complexity, create depth map estimate. Thereafter, the using estimate or an adjusted map. complexity.
lens.org参考文章(24)
Przemyslaw Kozankiewicz, Fast algorithm for creating image-based stereo images WSCG (Short Papers). pp. 59- 66 ,(2002)
Joseph Krahn, Michael Epstein, Nathan Newman, Method and apparatus for converting two-dimensional images into three-dimensional images ,(2004)
Manbae Kim, Sanghoon Park, Youngran Cho, Object-Based Stereoscopic Conversion of MPEG-4 Encoded Data Advances in Multimedia Information Processing - PCM 2004. pp. 491- 498 ,(2004) , 10.1007/978-3-540-30543-9_62
Alan D. Trombla, Francesco G. Callari, Steve Sullivan, 2D to 3D image conversion ,(2006)
Wa James Tam, Liang Zhang, Generating a depth map from a two-dimensional source image for stereoscopic and multiview imaging ,(2006)
Philip Victor Harman, Julien Charles Flack, Simon Richard Fox, Conversion and encoding techniques ,(2002)
J. D. PETTIGREW, Physiology of Color and Pattern Vision Photochemistry and Photobiology. ,vol. 13, pp. 511- 511 ,(1971) , 10.1111/J.1751-1097.1971.TB06146.X
Philip V. Harman, Julien Flack, Simon Fox, Mark Dowley, Rapid 2D to 3D conversion electronic imaging. ,vol. 4660, pp. 78- 86 ,(2002) , 10.1117/12.468020
Charles J. L. Best, Michael C. Kaye, Method for minimizing visual artifacts converting two-dimensional motion pictures into three-dimensional motion pictures ,(2003)