With the maturation of three-dimensional (3-D) technologies, display systems can provide higher visual quality to enrich the viewer experience. However, the depth information required for 3-D displays is not available in conventional 2-D recorded contents. Therefore, the conversion of existing 2-D video to 3-D video becomes an important issue for emerging 3-D applications. Our research members have paid attention on this problem for a long time. It can be trace back to B.C. 1999. From foreground segmentation, depth from depth cues, to perceptual depth generation, we try to construct a system which automatically converts 2-D videos to 3-D format. Various amounts of depth cues and lots of human perception knowledge are studied. Through the studies, a 3-D video processing pipeline is proposed and realized in Fig. 1. With this pipeline, all the conventional 2-D recorded contents can be converted to 3-D contents by stereoscopic views for human visual system (see Fig. 2) with 3-D displays.

Fig. 1. Three-Dimensional Video Processing Pipeline.

Fig. 2. Stereoscopic Views for Human Visual System



2D-to-3D conversion with perceptual depth cues (Depth cue promotion and integration) [ Webpage ]

Object-based depth post-processing [ Webpage ]

Comfort 3D reconstruction [ Webpage ]