Sub-Aperture Feature Adaptation in Single Image Super-Resolution Model for Light Field Imaging

The Light field (LF) imaging technology can obtain the spatial information and angular information of light simultaneously. Since, the sensor captures multiple images from different angular directions, the spatial resolution of each view image is limited. LF image super-resolution (SR) methods based on deep-learning have been proposed to solve this problem. However, correlation of LF image at two angular dimensions have not been fully exploited in algorithms that based on epipolar plane images (EPIs). In this paper, we propose a joint LF image SR network by combining a multiple magnification single image SR (SISR) network and an inpainting network for EPI solids. The EPI solids, which contain information of both angular dimensions, are extracted from the output of SISR network and used as input data of the inpainting network. The inpainting network uses channel attention mechanism in feature extraction module to extracting line and gradient feature contained by EPI solids and correlations between EPI slices of EPI sold for restoring the geometric continuity of different views. Experimental results show that the proposed multiple magnification spatial LF image SR network which is trained by dataset with mixed magnifications has better performance than other approaches that are specially trained at each magnification.

Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has brought lots of difficulties in developing related applications and becomes the main bottleneck of light field cameras. In this paper, a learning-based method using residual convolutional networks is proposed to reconstruct light fields with higher spatial resolution. The view images in one light field are first grouped into different image stacks with consistent sub-pixel offsets and fed into different network branches to implicitly learn inherent corresponding relations. The residual information in different spatial directions is then calculated from each branch and further integrated to supplement high-frequency details for the view image. Finally, a flexible solution is proposed to super-resolve entire light field images with various angular resolutions. Experimental results on synthetic and real-world datasets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in both visual and numerical evaluations. Furthermore, the proposed method shows good performances in preserving the inherent epipolar property in light field images.

Light field image (LFI) now is becoming increasingly popular in immersive media applications. Unlike traditional 2D and 3D images, images taken by light field cameras can capture both angular and spatial information. However, the spatial and angular information of LFI is highly inter-twined with varying disparities, which poses a higher challenge to the quality assessment of LFI. To address this issue, this paper proposes a full-reference light field image quality assessment (LFIQA) index that attempts to disentangle the coupling information from macro-pixel image (MacPI) to accurately evaluate the entire LFI quality. The proposed framework can be divided into three steps. Firstly, the LFIs are converted into the MacPIs, and then the spatial and angular feature maps are disentangled by using the spatial, angular and epipolar plane image (EPI) convolutions in the MacPI mode. Secondly, the structural similarity (SSIM) maps are calculated between the disentangled feature maps of the original and distorted LFIs. Furthermore, the quality-aware features of LFIs are extracted on the SSIM maps by utilized local binary patterns (LBP) and natural scene statistics (NSS). Finally, support vector regression (SVR) is utilized to predict the qualities of LFIs. Extensive experiments show that the proposed model outperforms multiple classical and state-of-the-art methods.

We present a deep neural network called the light field generative adversarial network (LFGAN) that synthesizes a 4D light field from a single 2D RGB image. We generate light fields using a single image super-resolution (SISR) technique based on two important observations. First, the small baseline gives rise to the high similarity between the full light field image and each sub-aperture view. Second, the occlusion edge at any spatial coordinate of a sub-aperture view has the same orientation as the occlusion edge at the corresponding angular patch, implying that the occlusion information in the angular domain can be inferred from the sub-aperture local information. We employ the Wasserstein GAN with gradient penalty (WGAN-GP) to learn the color and geometry information from the light field datasets. The network can generate a plausible 4D light field comprising 8×8 angular views from a single sub-aperture 2D image. We propose new loss terms, namely epipolar plane image (EPI) and brightness regularization (BRI) losses, as well as a novel multi-stage training framework to feed the loss terms at different time to generate superior light fields. The EPI loss can reinforce the network to learn the geometric features of the light fields, and the BRI loss can preserve the brightness consistency across different sub-aperture views. Two datasets have been used to evaluate our method: in addition to an existing light field dataset capturing scenes of flowers and plants, we have built a large dataset of toy animals consisting of 2,100 light fields captured with a plenoptic camera. We have performed comprehensive ablation studies to evaluate the effects of individual loss terms and the multi-stage training strategy, and have compared LFGAN to other state-of-the-art techniques. Qualitative and quantitative evaluation demonstrates that LFGAN can effectively estimate complex occlusions and geometry in challenging scenes, and outperform other existing techniques.

Light field imaging is an emerging technology in computational photography areas. Based on innovative designs of the imaging model and the optical path, light field cameras not only record the spatial intensity of threedimensional (3D) objects, but also capture the angular information of the physical world, which provides new ways to address various problems in computer vision, such as 3D reconstruction, saliency detection, and object recognition. In this paper, three key aspects of light field cameras, i.e., model, calibration, and reconstruction, are reviewed extensively. Furthermore, light field based applications on informatics, physics, medicine, and biology are exhibited. Finally, open issues in light field imaging and long-term application prospects in other natural sciences are discussed.

Light Field, a computational photography technique has various exciting features like refocusing and novel view synthesis. Previous works in light field photography have focused their work on creating light field images having a limited field of view. This limitation of light field images motivates the research for a acquisition system which can capture light field images with larger field of view. Recent works have been done to acquire light fields using a cylindrical arrangement of cameras which resolve the conventional complexity issue of acquisition of light field and subsequently merging them by essentially combining the capture and merging processes into a single exercise. We use this cylindrical system to generate a novel True Zoomed Light field panorama from the captured light field, which gives a wide 360? field of view similar to traditional panoramas along with the zoom applied to the whole panorama. The captured panorama can also be manipulated in various ways as is possible with other light field recordings. Also various zooming options which can be easily found in traditional camera, either tends to change the relative shape of the objects in image or introduces pix-elation effect. We use true zoom so as to improvise the zooming effect. We generate novel “True Zoomed Light Field Panorama” using our system. This type of panorama gives user a feeling of being closer to or farther from the whole environment at the same time.

No-reference light field image quality assessment based on depth, structural and angular information

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing unsupervised real-world SISR methods adopt a two-stage training strategy by synthesizing realistic LR images from their HR counterparts first, then training the super-resolution (SR) models in a supervised manner. However, the training of image degradation and SR models in this strategy are separate, ignoring the inherent mutual dependency between downscaling and its inverse upscaling process. Additionally, the ill-posed nature of image degradation is not fully considered. In this paper, we propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly. The main idea of SDFlow is to decouple image content and degradation information in the latent space, where content information distribution of LR and HR images is matched in a common latent space. Degradation information of the LR images and the high-frequency information of the HR images are fitted to an easy-to-sample conditional distribution. Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.

Traditional works have shown that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Make full use of these multi-scale information can improve the image restoration performance. However, the current proposed deep learning based restoration methods do not take the multi-scale information into account. In this paper, we propose a dilated convolution based inception module to learn multi-scale information and design a deep network for single image super-resolution. Different dilated convolution learns different scale feature, then the inception module concatenates all these features to fuse multi-scale information. In order to increase the reception field of our network to catch more contextual information, we cascade multiple inception modules to constitute a deep network to conduct single image super-resolution. With the novel dilated convolution based inception module, the proposed end-to-end single image super-resolution network can take advantage of multi-scale information to improve image super-resolution performance. Experimental results show that our proposed method outperforms many state-of-the-art single image super-resolution methods.

Light field cameras can capture comprehensive light information within a scene. Their core architecture incorporates a micro-lens array (MLA) positioned in front of the imaging sensor, mimicking the compound eye structure of insects. By processing the acquired data, these cameras enable the reconstruction of 3D spatial information. Despite their numerous advantages, light field cameras suffer from a critical drawback: low spatial resolution. To address this limitation, this study proposes a high-spatial-resolution light field imaging approach based on unidirectional object motion (UOMLF). A non-focused light field camera equipped with a hexagonally arranged MLA was developed as the foundation for a unidirectional object motion platform. Additionally, a 3D reconstruction algorithm tailored to high-resolution light field imaging was designed to complement this system. Experimental evaluations were conducted using the USAF resolution test chart and detector chip leads. Results demonstrate that the proposed method significantly enhances xy-plane resolution (approximately four times improvement) while maintaining z-axis resolution. This high-spatial-resolution light field technique based on unidirectional object motion offers broad potential for applications in both industrial and scientific fields.

Ear recognition is an emerging research area in image-based biometrics. The commercial availability of lenslet light field cameras able to capture full spatio-angular information has brought momentum to biometric and forensic research exploiting this new type of imaging sensors. This study is the first to consider the usage of light field cameras for ear recognition, proposing both an appropriate content database and an ear recognition solution. The novel Lenslet Light Field Ear DataBase (LLFEDB) includes 536 light field images corresponding to four different poses, from 67 subjects, captured with a Lytro ILLUM lenslet light field camera. The LLFEDB includes critical cases such as ear images partly occluded by ear piercing, earing, hair and combination of occlusions. The novel light field-based ear recognition solution proposed exploits the richer spatio-angular information available in the light field images. A comparative performance evaluation study using the LLFEDB, and focusing on the most recent light field and non-light field based descriptors for ear recognition, shows a very promising performance of the proposed descriptor, outperforming all the assessed descriptors.

Light field (LF) image super-resolution (SR) aims at reconstructing high-resolution LF images from their low-resolution counterparts. Although CNN-based methods have achieved remarkable performance in LF image SR, these methods cannot fully model the non-local properties of the 4D LF data. In this paper, we propose a simple but effective Transformer-based method for LF image SR. In our method, an angular Transformer is designed to incorporate complementary information among different views, and a spatial Transformer is developed to capture both local and long-range dependencies within each sub-aperture image. With the proposed angular and spatial Transformers, the beneficial information in an LF can be fully exploited and the SR performance is boosted. We validate the effectiveness of our angular and spatial Transformers through extensive ablation studies, and compare our method to recent state-of-the-art methods on five public LF datasets. Our method achieves superior SR performance with a small model size and low computational cost. Code is available at https://github.com/ZhengyuLiang24/LFT.

In this paper, an aberration correction method for an extended target is proposed to solve the problem of the lenslet-based plenoptic camera not imaging clearly under the influence of aberrations. We propose a light field manipulation method to improve performance of the light field imaging system. The principle of this method is that the sub-aperture images extracted from the raw light field image are offset when the light field imaging system is affected by aberrations, and the symmetrical arrangement of the sub-aperture image array is destroyed. By repairing the symmetrical arrangement of the sub-aperture image array, the influence of phase aberrations on the imaging system can be eliminated, and the resolution of the plenoptic camera can be improved. We use an image correlation algorithm to process the sub-aperture images of the plenoptic camera, calculate and compensate each sub-aperture image's displacement caused by aberrations, and restore the symmetrical arrangement of the sub-aperture image array; then, a corrected high-resolution refocused image can be generated. In particular, this method uses only the raw light field information obtained by the plenoptic camera in a single exposure, without adding other hardware devices. Furthermore, it takes the extended target itself as the reference image, so the ideal position need not be calibrated in advance. Also, the parallax information of the sub-aperture images is retained, and the method is simple and easy to use. Numerical simulation and experimental results show that the technology proposed in this paper can work well for high-resolution imaging of a plenoptic camera with phase aberrations. This method can be potentially applied to analyze lens aberration, media-induced image distortion such as water turbulence in underwater imaging, and atmospheric turbulence in remote imaging. It may have important application prospects in the fields of astronomical object detection, remote sensing, etc.

Light field image becomes one of the most promising media types for immersive video applications. In this paper, we propose a novel end-to-end spatial-angular-decorrelated network (SADN) for high-efficiency light field image compression. Different from the existing methods that exploit either spatial or angular consistency in the light field image, SADN decouples the angular and spatial information by dilation convolution and stride convolution in spatial-angular interaction, and performs feature fusion to compress spatial and angular information jointly. To train a stable and robust algorithm, a large-scale dataset consisting of 7549 light field images is proposed and built. The proposed method provides 2.137 times and 2.849 times higher compression efficiency relative to H.266/VVC and H.265/HEVC inter coding, respectively. It also outperforms the end-to-end image compression networks by an average of 79.6% bitrate saving with much higher subjective quality and light field consistency.

Light field (LF) image super-resolution (SR) can improve the limited spatial resolution of LF images by using complementary information from different perspectives. However, current LF image SR methods only use the RGB data to implicitly exploit the information among different perspectives, without paying attention to the information loss from raw data to RGB data and the explicit structure information utilization. To address the first issue, a data generation pipeline is developed to collect LF raw data for LF image SR. In addition, to make full use of the multiview information, an end-to-end convolutional neural network architecture (namely, LF-RawSR) is proposed for LF image SR. Specifically, an aggregated module is first used to fuse the angular information based on a volume transformer with plane sweep volume. Then the aggregated feature is warped to all LF views using a cross-view transformer for nonlocal dependencies utilization. The experimental results demonstrate that our method outperforms existing state-of-the-art methods with a comparative computational cost, and fine details and clear structures can be restored.