Dense Light Field Reconstruction From Sparse Sampling Using Residual Network
share
Light field records numerous light rays from real-world scene. However, capturing a dense light field by existing devices is a time-consuming process. Reconstructing a large amount of light rays equivalent to multiple light fields using sparse sampling arises a severe challenge for existing methods. In this paper, we present a learning based approach to reconstruct multiple light fields between two mutually independent light fields. We indicate that light rays distributed in different light fields have some consistent constraints under a certain condition. The most significant constraint is a depth related correlation between angular and spatial dimensions. Our method avoids working out the error-sensitive constraints by employing a deep neural network. We solve residual values of pixels on the epipolar plane image (EPI) to reconstruct novel light fields. Our method is able to reconstruct 4X up-sampling, i.e., extrapolating four novel light fields between two mutually independent light fields. We also compare our results with those yielded by a number of alternatives elsewhere in the literature, which shows our reconstructed light fields have better structure similarity and occlusion relationship.
READ FULL TEXT
