Depth estimation for hand-held light field cameras under low light conditions

Min-Hung Chen, Ching-Fan Chiang, Yi-Chang Lu

Abstract: Depth estimation is one of the new functions provided by hand-held light field cameras. However, the quality of depth estimation is very sensitive to noise, which is especially a problem for scenes under low light conditions. In this paper, we propose a depth estimation flow for light field data, which can be fully-automated and no noise characteristics are required a priori. The results of Root Mean Square Error (RMSE) and Percentage of Bad Matching Pixels (PBM) show the effectiveness of this iterative correlation-based depth estimation flow even with basic filtering functions.