Multi-Models Fusion for Light Field Angular Super-Resolution

Abstract

Light field (LF) imaging has received increasing attention due to its richer interpretation of the scene. However, an inherent spatial-angular trade-off exists in LF that prevents LF from practical applications. Consequently, how to break such a trade-off has become one of the main challenges in sparsely sampled LF reconstruction. LF super-resolution (SR) can provide an opportunity to solve this issue, but most methods exploit only one form of LF, thereby leading to much loss of information. We believe that different LF forms can compensate each other to obtain higher gains via fusion strategy. In this paper, therefore, we propose a multi-models fusion for LF SR in angular domain. Cascading models which are trained by different LF forms can fully exploit rich LF information. Experimental results demonstrate that our method is effective and achieves a comparable result against state-of-the-art techniques.

A New Parallel Intelligence Based Light Field Dataset for Depth Refinement and Scene Flow Estimation

“…Another technique is warping disparities with the reference view and blend to the target view [ 31 ]. To eliminate trade-offs between the spatial and angular domains and fully utilize the abundant light field data, Cao [ 32 ] proposed a multi-model fusion in light field angular super-resolution estimation. By effectively exploiting the intrinsic geometry information, Jin [ 29 ] developed an end-to-end learning-based approach capable of angularly super-resolving a sparsely sampled light field with a large baseline.…”

Reivew of Light Field Image Super-Resolution

“…Ma [58] used the most advanced technology of SISR to handle the light field superresolution task and developed a flexible light field super-resolution network model based on the RDN network. Cao [71] used several different models to deal with the light field image angle super-resolution task under different image forms, and then merged these models to make full use of the light field image's own information. Guo [72] indicated that light rays distributed in different light fields have the same constraint under certain conditions and used the residual network to reduce the error-prone constraints.…”