Residual Networks for Light Field Image Super-Resolution

Learning from EPI-Volume-Stack for Light Field image angular super-resolution

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.

Learning an epipolar shift compensation for light field image super-resolution

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.

As light field images continue to increase in use and application, it becomes necessary to adapt existing image processing methods to this unique form of photography. In this paper we explore methods for applying neural style transfer to light field images. Feed-forward style transfer networks provide fast, high-quality results for monocular images, but no such networks exist for full light field images. Because of the size of these images, current light field data sets are small and are insufficient for training purely feed-forward style-transfer networks from scratch. Thus, it is necessary to adapt existing monocular style transfer networks in a way that allows for the stylization of each view of the light field while maintaining visual consistencies between views. To do this, we first generate disparity maps for each view given a single depth image for the light field. Then in a fashion similar to neural stylization of stereo images, we use disparity maps to enforce a consistency loss between views and to warp feature maps during the feed forward stylization. Unlike previous work, however, light fields have too many views to train a purely feed-forward network that can stylize the entire light field with angular consistency. Instead, the proposed method uses an iterative optimization for each view of a single light field image that backpropagates the consistency loss through the network. Thus, the network architecture allows for the incorporation of pre-trained fast monocular stylization network while avoiding the need for a large light field training set.

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.

The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic geometry information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48×. In addition, our method preserves the light field parallax structure better.

Light field images taken by plenoptic cameras often have a tradeoff between spatial and angular resolutions. In this paper, we propose a novel spatial super-resolution approach for light field images by jointly exploiting internal and external similarities. The internal similarity refers to the correlations across the angular dimensions of the 4D light field itself, while the external similarity refers to the cross-scale correlations learned from an external light field dataset. Specifically, we advance the classic projection-based method that exploits the internal similarity by introducing the intensity consistency checking criterion and a back-projection refinement, while the external correlation is learned by a CNN-based method which aggregates all warped high-resolution sub-aperture images upsampled from the low-resolution input using a single image super-resolution method. By analyzing the error distributions of the above two methods and investigating the upperbound of combining them, we find that the internal and external similarities are complementary to each other. Accordingly, we further propose a pixel-wise adaptive fusion network to take advantage of both their merits by learning a weighting matrix. Experimental results on both synthetic and real-world light field datasets validate the superior performance of the proposed approach over the state-of-the-arts.

With the availability of commercial Light Field (LF) cameras, LF imaging has emerged as an up-and-coming technology in computational photography. However, the spatial resolution is significantly constrained in commercial micro-lens-based LF cameras because of the inherent multiplexing of spatial and angular information. Therefore, it becomes the main bottleneck for other applications of light field cameras. This paper proposes an adaptation module in a pre-trained Single Image Super-Resolution (SISR) network to leverage the powerful SISR model instead of using highly engineered light field imaging domain-specific Super Resolution models. The adaption module consists of a Sub-aperture Shift block and a fusion block. It is an adaptation in the SISR network to further exploit the spatial and angular information in LF images to improve the super-resolution performance. Experimental validation shows that the proposed method outperforms existing light field super-resolution algorithms. It also achieves PSNR gains of more than 1 dB across all the datasets as compared to the same pre-trained SISR models for scale factor 2, and PSNR gains 0.6 − 1 dB for scale factor 4.

Light field (LF) imaging has gained significant attention due to its recent success in microscopy, 3-dimensional (3D) displaying and rendering, augmented and virtual reality usage. Postprocessing of LF enables us to extract more information from a scene compared to traditional cameras. However, the use of LF is still a research novelty because of the current limitations in capturing high-resolution LF in all of its four dimensions. While researchers are actively improving methods of capturing high-resolution LF's, using simulation, it is possible to explore a high-quality captured LF's properties. The immediate concerns following the LF capture are its storage and processing time. A rich LF occupies a large chunk of memory ---order of multiple gigabytes per LF---. Also, most feature extraction techniques associated with LF postprocessing involve multi-dimensional integration that requires access to the whole LF and is usually time-consuming. Recent advancements in computer processing units made it possible to simulate realistic images using physical-based rendering software. In this work, at first, a transformation function is proposed for building a camera array (CA) to capture the same portion of LF from a scene that a standard plenoptic camera (SPC) can acquire. Using this transformation, LF simulation with similar properties as a plenoptic camera will become trivial in any rendering software. Artificial intelligence (AI) and machine learning (ML) algorithms ---when deployed on the new generation of GPUs--- are faster than ever. It is possible to generate and train large networks with millions of trainable parameters to learn very complex features. Here, residual convolutional neural network (RCNN) structures are employed to build complex networks for compression and feature extraction from an LF. By combining state-of-the-art image compression and RCNN, I have created a compression pipeline. The proposed pipeline's bit per pixel (bpp) ratio is 0.0047 on average. I show that with a 1% compression time cost and 18x speedup for decompression, our methods reconstructed LFs have better structural similarity index metric (SSIM) and comparable peak signal-to-noise ratio (PSNR) compared to the state-of-the-art video compression techniques used to compress LFs. In the end, using RCNN, I created a network called RefNet, for extracting a group of 16 refocused images from a raw LF. The training parameters of the 16 LFs are set to (\alpha=0.125, 0.250, 0.375, ..., 2.0) for training. I show that RefNet is 134x faster than the state-of-the-art refocusing technique. The RefNet is also superior in color prediction compared to the state-of-the-art

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.

Currently, a raw light field image can be captured by a light field camera and decomposed into multi-views with different perceptual quality. A novel light field compression approach for a light field image is proposed based on this observation, where the raw light field image is decomposed into multi-views as pseudo-sequencing frames and reordered according to their perceptual quality. The resulting pseudo-temporal sequence is then compressed by high-efficiency video coding (HEVC) encoder. Experimental results show that the proposed method can achieve a better coding performance (up to 28% Bjontegaard delta bit rate reduction (BDBR) savings) compared with state-of-the-art reordering techniques using HEVC.

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.

With the introduction of consumer light field cameras, light field imaging has recently become widespread. However, there is an inherent trade-off between the angular and spatial resolution, and thus, these cameras often sparsely sample in either spatial or angular domain. In this paper, we use machine learning to mitigate this trade-off. Specifically, we propose a novel learning-based approach to synthesize new views from a sparse set of input views. We build upon existing view synthesis techniques and break down the process into disparity and color estimation components. We use two sequential convolutional neural networks to model these two components and train both networks simultaneously by minimizing the error between the synthesized and ground truth images. We show the performance of our approach using only four corner sub-aperture views from the light fields captured by the Lytro Illum camera. Experimental results show that our approach synthesizes high-quality images that are superior to the state-of-the-art techniques on a variety of challenging real-world scenes. We believe our method could potentially decrease the required angular resolution of consumer light field cameras, which allows their spatial resolution to increase.

Light field angular super-resolution based on intrinsic and geometric information