An Effective Hybrid Depth-Generation Algorithm for 2D-to-3D Conversion in 3D Displays

In recent years, 3D display technology has been receiving increasingly more attention. The most intuitive 3D method is to use two temporally synchronized video streams for the left and right eyes, respectively. However, traditional 2D video contents are captured by one camera, and in order to synthesize the left and right views as the behavior of two cameras, depth map information is required. In this paper, we propose a hybrid algorithm for 2D-to-3D conversion in 3D displays; it is a good way to solve the problem of traditional 2D video contents which need to generate 3D effects in 3D displays. We choose three depth cues for depth estimation: motion information, linear perspective, and texture characteristics. Moreover, we adopt a bilateral filter for depth map smoothing and noise removal. From the experimental results, execution time can be reduced by 25%-35% and the depth perception score is between 75 and 85. Thus, the human eye cannot sense the noticeable differences from the final 3D rendering. Furthermore, it is very suitable to apply our proposed hybrid algorithm to 2D-to-3D conversion in 3D displays.