We propose shearlet decomposition based light field (LF) reconstruction and filtering techniques for mitigating artifacts in the visualized contents of 3D multiview displays. Using the LF reconstruction capability, we first obtain the densely sampled light field (DSLF) of the scene from a sparse set of view images. We design the filter via tiling the Fourier domain of epipolar image by shearlet atoms that are directionally and spatially localized versions of the desired display passband. In this way, it becomes possible to process the DSLF in a depth-dependent manner. That is, the problematic areas in the 3D scene that are outside of the display depth of field (DoF) can be selectively filtered without sacrificing high details in the areas near the display, i.e. inside the DoF. The proposed approach is tested on a synthetic scene and the improvements achieved by means of the quality of the visualized content are verified, where the visualization process is simulated using a geometrical optics model of the human eye.
Erdem Sahin, Suren Vagharshakyan, Robert Bregovic, Gwangsoon Lee, Atanas Gotchev, "Conversion of sparsely-captured light field into alias-free full-parallax multiview content" in Proc. IS&T Int’l. Symp. on Electronic Imaging: Stereoscopic Displays and Applications XXIX, 2018, pp 144-1 - 144-5, https://doi.org/10.2352/ISSN.2470-1173.2018.04.SDA-144