Generating dense depth maps using a patch cloud and local planar surface models

Patch cloud based multi-view stereo methods have proven to be an accurate and scalable approach for scene reconstruction. Their applicability, however, is limited due to the semi-dense nature of their reconstruction. We propose a method to gener-ate a dense depth map from a patch cloud by assuming a pla-nar surface model for non-reconstructed areas. We use local evidence to estimate the best fitting plane around missing ar-eas. We then apply a graph cut optimization to select the best plane for each pixel. We demonstrate our approach with a challenging scene containing planar and non-planar surfaces. Index Terms — Computer vision, Stereo image process-in