The low spatial resolution of light-field image poses significant difficulties in exploiting its advantage. To mitigate the dependency of accurate depth or disparity information as priors for light-field image super-resolution, we propose an implicitly multi-scale fusion scheme to accumulate contextual information from multiple scales for super-resolution reconstruction. The implicitly multi-scale fusion scheme is then incorporated into bidirectional recurrent convolutional neural network, which aims to iteratively model spatial relations between horizontally or vertically adjacent sub-aperture images of light-field data. Within the network, the recurrent convolutions are modified to be more effective and flexible in modeling the spatial correlations between neighboring views. A horizontal sub-network and a vertical sub-network of the same network structure are ensembled for final outputs via stacked generalization. Experimental results on synthetic and real-world data sets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in peak signal-to-noise ratio and gray-scale structural similarity indexes, which also achieves superior quality for human visual systems. Furthermore, the proposed method can enhance the performance of light field applications such as depth estimation.

Multi-view properties of light field (LF) imaging enable exciting applications such as auto-refocusing, depth estimation and 3D reconstruction. However, limited angular resolution has become the main bottleneck of microlens-based plenoptic cameras towards more practical vision applications. Existing view synthesis methods mainly break the task into two steps, i.e. depth estimating and view warping, which are usually inefficient and produce artifacts over depth ambiguities. We have proposed an end-to-end deep learning framework named Pseudo 4DCNN to solve these problems in a conference paper. Rethinking on the overall paradigm, we further extend pseudo 4DCNN and propose a novel loss function which is applicable for all tasks of light field reconstruction i.e. EPI Structure Preserving (ESP) loss function. This loss function is proposed to attenuate the blurry edges and artifacts caused by averaging effect of L2 norm based loss function. Furthermore, the extended Pseudo 4DCNN is compared with recent state-of-the-art (SOTA) approaches on more publicly available light field databases, as well as self-captured light field biometrics and microscopy datasets. Experimental results demonstrate that the proposed framework can achieve better performances than vanilla Pseudo 4DCNN and other SOTA methods, especially in the terms of visual quality under occlusions. The source codes and self-collected datasets for reproducibility will be available online soon.

Computational photography is a combination of novel optical designs and processing methods to capture high‐dimensional visual information. As an emerged promising technique, light field (LF) imaging measures the lighting, reflectance, focus, geometry and viewpoint in the free space, which has been widely explored for depth estimation, view synthesis, refocus, rendering, 3D displays, microscopy and other applications in computer vision in the past decades. In this paper, the authors present a comprehensive research survey on the LF imaging theory, technology and application. Firstly, the LF imaging process based on a MicroLens Array structure is derived, that is MLA‐LF. Subsequently, the innovations of LF imaging technology are presented in terms of the imaging prototype, consumer LF camera and LF displays in Virtual Reality (VR) and Augmented Reality (AR). Finally the applications and challenges of LF imaging integrating with deep learning models are analysed, which consist of depth estimation, saliency detection, semantic segmentation, de‐occlusion and defocus deblurring in recent years. It is believed that this paper will be a good reference for the future research on LF imaging technology in Artificial Intelligence era.

This paper presents a hierarchical baseline stereo-matching framework for depth estimation using a novelly developed light field camera. The imaging process of a micro-lens array-based light field camera is derived. A macro-pixel map is constructed by treating each micro-lens as one macro-pixel in the light field’s raw image. For each macro-pixel, a feature vector is represented by leveraging texture and gradient cues over the surrounding ring of neighboring macro-pixels. Next, the micro-lenses containing edges are detected on the macro-pixel map. Hierarchical baseline stereo-matching is performed by macro-pixel-wise coarse matching and pixel-wise fine matching, effectively eliminating matching ambiguities. Finally, a post-processing step is applied to improve accuracy. The lab-designed light field camera’s imaging performance is evaluated in terms of accuracy and processing speed by capturing real-world scenes under studio lighting conditions. And an experiment using rendered synthetic samples is conducted for quantitative evaluation, showing that depth maps with local details can be accurately recovered.

Diabetic retinopathy (DR), a critical ocular disease that can lead to blindness, demands early and accurate diagnosis to prevent vision loss. Current automated DR diagnosis methods face two core challenges: first, subtle early lesions such as microaneurysms are often missed due to insufficient feature extraction; second, there is a persistent trade-off between model accuracy and efficiency—lightweight architectures often sacrifice precision for real-time performance, while high-accuracy models are computationally expensive and difficult to deploy on resource-constrained edge devices. To address these issues, this study presents a novel deep learning framework integrating depthwise separable convolution and a multi-view attention mechanism (MVAM) for efficient DR diagnosis using retinal images. The framework employs multi-scale feature fusion via parallel 3 × 3 and 5 × 5 convolutions to capture lesions of varying sizes and incorporates Gabor filters to enhance vascular texture and directional lesion modeling, improving sensitivity to early structural abnormalities while reducing computational costs. Experimental results on both the diabetic retinopathy (DR) dataset and ocular disease (OD) dataset demonstrate the superiority of the proposed method: it achieves a high accuracy of 0.9697 on the DR dataset and 0.9669 on the OD dataset, outperforming traditional methods such as CNN_eye, VGG, and UNet by more than 1 percentage point. Moreover, its training time is only half that of U-Net (on DR dataset) and VGG (on OD dataset), highlighting its potential for clinical DR screening.