A hybrid approach for image super-resolution of light field images

Recent advances in camera technologies has led to the design of plenoptic cameras. This camera type can capture multiple images of the same scene using arrays of microlenses, where each microlens has a shifted location providing a separate view of the scene. Such a design results in a superior performance as compared to traditional cameras, enabling multi-view or multi-focal imaging captured in a single shot. However, currently available plenoptic cameras are limited in spatial resolution, which makes it difficult to use them in applications where sharpness or high resolution is key, such as the film industry. Our paper presents a novel light field hybrid super-resolution method that combines two classical super-resolution techniques for efficient application to plenoptic images. After this combination, we first segment the output hybrid super-resolution image into the objects of interest. Afterward, we apply sparse representation to super resolve the segmented image. This technique helps to improve the quality by decrease computations for light field images and extract significant features from the objects of interest. We demonstrate the gain achieved by the novel method as compared to the current relevant approaches in terms of both PSNR and SSIM for various enhanced spatial resolutions.