Automatic depth map generation from reconstructed 3D points

We propose a novel method to automatically generate a depth map of static background region from 3D reconstructed points. First, camera parameters and 3D points are reconstructed by SfM technique. Next, depth values of the 3D points are computed and the values are spreaded in 2D image domain. Finally post-processing to deal with over-lapped depth informations and reduce flickering artifact is followed. The proposed method generates 2D depth map images directly from camera parameters and 3D points and so it is faster and more stable than previous methods. The generated depth map can be used for 2Dto3D converting and contents retrieval, etc.