High-Fidelity Light Field Reconstruction Method Using View-Selective Angular Feature Extraction

Deep learning (DL) provides an effective approach for light field (LF) reconstruction that aims to synthesize novel views from sparsely-sampled views. However, it is challenging to address domain asymmetry when adopting spatial-angular interaction LF reconstruction methods. To overcome this problem, a view-selective angular feature extraction block (VS-LFAFE) is proposed to obtain full-resolution angular features that enumerate whole viewpoints in a macropixel. By applying the VS-LFAFE, a novel LF reconstruction method is proposed, consisting of two subblocks: a spatial-angular feature extraction and fusion block, and an angular upsampling block. Experimental results demonstrate the effectiveness of the VS-LFAFE, and validate that the proposed method can achieve superior performance compared with the state-of-the-art methods.