Non-redundant rendering for efficient multi-view scene discretization

A powerful approach for managing scene complexity is to sample the scene with a set of images. However, conventional images from nearby viewpoints have a high level of redundancy, which reduces scene sampling efficiency. We present non-redundant rendering, which detects and avoids redundant samples as the image is computed. We show that non-redundant rendering leads to improved scene sampling quality according to several view-independent and view-dependent metrics, compared to conventional scene discretization using redundant images and compared to depth peeling. Non-redundant images have a higher degree of fragmentation and, therefore, conventional approaches for scene reconstruction from samples are ineffective. We present a novel reconstruction approach that is well suited to scene discretization by non-redundant rendering. Finally, we apply non-redundant rendering and scene reconstruction techniques to soft shadow rendering where we show that our approach has an accuracy advantage over conventional images and over depth peeling.