A real-time 1080p 2D-to-3D video conversion system

Author

Tsai, Sung-Fang ; Cheng, Chao-Chung ; Li, Chung-Te ; Chen, Liang-Gee

Author_Institution

Grad. Inst. of Electron. Eng., Nat. Taiwan Univ., Taipei, Taiwan

Volume

57

Issue

2

fYear

2011

fDate

5/1/2011 12:00:00 AM

Firstpage

915

Lastpage

922

Abstract

In this paper, we demonstrate a 2D-to-3D video conversion system capable of real-time 1920×1080p conversion. The proposed system generates 3D depth information by fusing cues from edge feature-based global scene depth gradient and texture-based local depth refinement. By combining the global depth gradient and local depth refinement, generated 3D images have comfortable and vivid quality, and algorithm has very low computational complexity. Software is based on a system with a multi-core CPU and a GPU. To optimize performance, we use several techniques including unified streaming dataflow, multi-thread schedule synchronization, and GPU acceleration for depth image-based rendering (DIBR). With proposed method, real-time 1920×1080p 2Dto- 3D video conversion running at 30fps is then achieved.

Keywords

computational complexity; computer graphic equipment; coprocessors; edge detection; image texture; multi-threading; multiprocessing systems; natural scenes; real-time systems; rendering (computer graphics); video signal processing; 3D depth information; 3D image generation; DIBR; GPU acceleration; computational complexity; depth image-based rendering; edge feature-based global scene depth gradient; multicore CPU; multithread schedule synchronization; real-time 2D-to-3D video conversion system; texture-based local depth refinement; unified streaming dataflow; Graphics processing unit; Image color analysis; Pixel; Real time systems; Rendering (computer graphics); Streaming media; Three dimensional displays; 2D-to-3D conversion; 3D video; Depth map generation; real-time implementation;

fLanguage

English

Journal_Title

Consumer Electronics, IEEE Transactions on

Publisher

ieee

ISSN

0098-3063

Type

jour

DOI

10.1109/TCE.2011.5955240

Filename

5955240