Depth Map Generation Using Local Depth Hypothesis for 2d-to-3d Conversion

A single two dimensional (2D) image does not contain depth information. An infinite number of points in the three dimensional (3D) space are projected to the same point in the image plane. But a single 2D image has some monocular depth cues, by which we can make a hypothesis of depth variation in the image to generate a depth map. This paper proposes an interactive method of depth map generation from a single image for 2D-to-3D conversion. Using a hypothesis of depth variation can reduce the human effort to generate a depth map. The only thing required from a user is to mark some salient regions to be distinguished with respect to depth variation. The proposed algorithm makes hypothesis of each salient region and generates a depth map of an input image. Experimental results show that the proposed method gives natural depth map in terms of human perception.