Frequency Descriptor based Light Field Depth Estimation
Junke Li, Xin Jin · 2019
Depth estimation plays an important role in light field data processing. However, conventional focus measurement based approaches fail at the angular patches containing occlusion boundaries. In this paper, a novel depth estimation algorithm is proposed based on frequency descriptors. On the basis of the imaging process analysis, we propose to first perform the occlusion discrimination and edge orientation extraction in the frequency domain for the spatial patch from the central sub-aperture image. Then, according to the occlusion orientation, a variable-block-size angular patch is selected in the normal direction to construct the frequency descriptors for focus measurement in the focal stack. Experimental results demonstrate superior performance of the proposed method in robustness and depth accuracy.