A novel rendering approach for unstructured light field interpolation

In this paper, a novel framework is proposed for light field reconstruction from a sparse set of views. The light field is the unstructured, and has the large disparity. We indicate that the reconstruction can be efficiently modeled as angular restoration on epipolar plane image (EPI). Based on “blur-restoration-deblur” framework, we analyze the EPI with Fourier transform. What’s more, a novel rendering approach is presented by combining proposed “blur-restoration-deblur” framework and depth information to handle large disparity and unstructured light field. We evaluate our approach on several datasets and demonstrate the high performance and robustness of the proposed framework compared with the state-of-the-arts algorithms.

Full Text (PDF format)

Published 7 February 2018