Abstract

Heavy occlusions in cluttered scenes impose significant chal- lenges to many computer vision applications. Recent light field imaging systems provide new see-through capabilities through synthetic aperture imaging (SAI) to overcome the occlusion problem. Existing synthetic aperture imaging methods, however, emulate focusing at a specific depth layer but is incapable of producing an all-in-focus see-through image. Al- ternative in-painting algorithms can generate visually plausible results but can not guarantee the correctness of the result. In this paper, we present a novel depth free all-in-focus SAI technique based on light- field visibility analysis. Specifically, we partition the scene into multiple visibility layers to directly deal with layer-wise occlusion and apply an optimization framework to propagate the visibility information between multiple layers. On each layer, visibility and optimal focus depth estima- tion is formulated as a multiple label energy minimization problem. The energy integrates the visibility mask from previous layers, multi-view in- tensity consistency, and depth smoothness constraint. We compare our method with the state-of-the-art solutions. Extensive experimental re- sults with qualitative and quantitative analysis demonstrate the effec- tiveness and superiority of our approach.