Light Field Super-Resolution Via Graph-Based Regularization

Light field cameras can capture the 3D information in a scene with a single shot. This special feature makes light field cameras very appealing for a variety of applications: from the popular post-capture refocus, to depth estimation and imagebased rendering. However, light field cameras suffer by design from strong limitations in their spatial resolution, which should therefore be augmented by computational methods. On the one hand, off-the-shelf single-frame and multi-frame super-resolution algorithms are not ideal for light field data, as they do not consider its particular structure. On the other hand, the few super-resolution algorithms explicitly tailored for light field data exhibit significant limitations, such as the need to estimate an explicit disparity map at each view. In this work we propose a new light field super-resolution algorithm meant to address these limitations. We adopt a multi-frame alike super-resolution approach, where the complementary information in the different light field views is used to augment the spatial resolution of the whole light field. We show that coupling the multi-frame approach with a graph regularizer, that enforces the light field structure via non local self similarities, permits to avoid the costly and challenging disparity estimation step for all the views. Extensive experiments show that the proposed algorithm compares favorably to the other state-of-the-art methods for light field super-resolution, both in terms of PSNR and in terms of visual quality. Moreover, differently from the other light field superresolution methods, the new algorithm provides reconstructed light field views with uniform quality, which happens to be an important feature for any light field application.