Spatial-Angular Interaction for Light Field Image Super-Resolution
arXiv:1912.07849
Abstract
Light field (LF) cameras record both intensity and directions of light rays, and capture scenes from a number of viewpoints. Both information within each perspective (i.e., spatial information) and among different perspectives (i.e., angular information) is beneficial to image super-resolution (SR). In this paper, we propose a spatial-angular interactive network (namely, LF-InterNet) for LF image SR. Specifically, spatial and angular features are first separately extracted from input LFs, and then repetitively interacted to progressively incorporate spatial and angular information. Finally, the interacted features are fused to superresolve each sub-aperture image. Experimental results demonstrate the superiority of LF-InterNet over the state-of-the-art methods, i.e., our method can achieve high PSNR and SSIM scores with low computational cost, and recover faithful details in the reconstructed images.
arXiv commentIn this version, we have revised the paper and compared our LF-InterNet to the most recent LF-ATO method (CVPR2020). Codes and pre-trained models are available at https://github.com/YingqianWang/LF-InterNet
References in corpus (6)
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- Deep Learning for Single Image Super-Resolution: A Brief Review
- Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolution
- High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction
- A Deep Journey into Super-resolution: A survey
- Deep Learning for Image Super-resolution: A Survey