Light-field spatial super-resolution via enhanced spatial-angular separable convolutional network

• Published in: Journal of electronic imaging 2022-09, Vol.31 (5), p.053030-053030
• Main Authors: Hua, Xiyao, Wang, Minghui, Su, Boni
• Format: Article
• Language: English
• ISSN: 1017-9909; 1560-229X
• DOI: 10.1117/1.JEI.31.5.053030

Light-field images captured by light-field cameras usually suffer from low spatial resolution due to the inherent limited sensor resolution. Light-field spatial super-resolution thus becomes increasingly desirable for subsequent applications. Although continuous progress has been achieved, the existing methods still failed to thoroughly explore the coherence among light-field views. To address this issue, we propose an efficient neural network for light-field spatial super-resolution, in which the spatial and angular information can be fully exploited by repeatedly alternating spatial and angular domain. Specifically, an enhanced spatial-angular separable convolution block is proposed to efficiently exploit the correlation information between sub-aperture images. Moreover, a multi-scale feature extraction block is introduced to extract feature representations at different scales and capture rich texture and semantic information. Experimental results on both synthetic and real-world light-field datasets demonstrate that the proposed method outperforms other state-of-the-art methods with higher peak signal-to-noise ratio (PSNR)/structural similarity (SSIM) values and fewer parameters.