Depth from defocus in presence of partial self occlusion

Abstract

Contrary to the normal belief we show that self occlusion is present in any real aperture image and we present a method on how we can take care of the occlusion while recovering the depth using the defocus as the cue. The space-variant blur is modeled as an MRF and the MAP estimates are obtained for both the depth map and the everywhere focused intensity image. The blur kernel is adjusted in the regions where occlusion is present, particularly at the regions of discontinuities in the scene. The performance of the proposed algorithm is tested over synthetic data and the estimates are found to be better than the earlier schemes where such subtle effects were ignored.