Light field (LF) imaging enables new possibilities for digital imaging, such as digital refocusing, changing of focus plane, changing of viewpoint, scene-depth estimation, and 3D scene reconstruction, by capturing both spatial and angular information of light rays. However, one main problem in dealing with LF data is its sheer volume. In this context, efficient compression methods are needed for such a particular type of content. In this paper, we propose a content-based LF image-compression method with Gaussian process regression to improve the compression efficiency and accelerate the prediction procedure. First, the LF image is fed to the intra-frame codec of HEVC. In the prediction procedure, the prediction units (PUs) are classified as non-homogenous texture units, homogenous texture units, and visually flat units, based on the content property of the LF image. For each category, we design a corresponding Gaussian process regression (GPR)-based prediction method. Moreover, we propose a classification mechanism to exactly decide to which category the current PU belongs, so as to adjust the trade-off between the computational burden and the LF image coding efficiency. Experimental results demonstrate that the proposed LF image compression method is superior to several other state-of-the-art compression methods in terms of different quality metrics. Furthermore, the proposed method can also achieve a good visual quality of views rendered from decoded LF contents.

The high dynamic range (HDR) image recovery from the low dynamic range (LDR) image aims to estimate HDR image by decompressing luminance range and enhancing details of the LDR input. In practical usages, when faced with the over-exposed, the under-exposed or the low-light images, the state-of-art prediction methods lack of the capability estimating the ideal HDR images from these LDR images in different light conditions. Aiming for this, in this paper, we propose a light adaptation HDR recovery framework, called LA-HDR, which includes the adaptive low-light, the mid-range and high-light details amplification and the multi-details fusion. Specifically, the framework predicts HDR images with two components: the multi-images generation for the detail amplification in different light ranges, and the final multi-images fusion. To create the multi-images, first, the designed bit-depth enhancement network (EnhanceNet) produces the high bit-depth result with the enhanced image contrast. This result can be furtherly processed by user-defined high bit-depth denoising method to refrain the low-light noise. Meanwhile, the proposed exposure bias network (EBNet) adaptively estimates the global exposure bias of the input image for robustly rectifying the mid-range details. With the enhanced result, the predicted exposure bias and the designed transfer functions, the details in the three light ranges are adaptively amplified into three multi-images, and they are fused by the designed multi-images fusion network (FuseNet) for the final HDR prediction. The amplification and fusion scheme ensures robust HDR recovery under different light conditions, while eliminating the high-light recovery artifacts from previous methods. The proposed fusion masks generation (FMG) and the global feature embedding (GFE) modules in FuseNet eliminate the fusion artifacts in the baseline network. Experimental results show that LA-HDR acquires the best average performance under various light conditions, and it receives low influence from the input light conditions among the tested state-of-art HDR recovery methods.