Light field imaging has emerged as a technology allowing to capture richer visual information from our world. As opposed to traditional photography, which captures a 2D projection of the light in the scene integrating the angular domain, light fields collect radiance from rays in all directions, demultiplexing the angular information lost in conventional photography. On the one hand, this higher dimensional representation of visual data offers powerful capabilities for scene understanding, and substantially improves the performance of traditional computer vision problems such as depth sensing, post-capture refocusing, segmentation, video stabilization, material classification, etc. On the other hand, the high-dimensionality of light fields also brings up new challenges in terms of data capture, data compression, content editing, and display. Taking these two elements together, research in light field image processing has become increasingly popular in the computer vision, computer graphics, and signal processing communities. In this paper, we present a comprehensive overview and discussion of research in this field over the past 20 years. We focus on all aspects of light field image processing, including basic light field representation and theory, acquisition, super-resolution, depth estimation, compression, editing, processing algorithms for light field display, and computer vision applications of light field data.

/pdf/light-field-image-processing-an-overview-3jq61afb1y.pdf

Light Field Image Processing: An Overview

numerical methods for partial differential equations is available in our digital library an online access to it is set as public so you can download it instantly. Our digital library hosts in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the numerical methods for partial differential equations is universally compatible with any devices to read.

Numerical Methods For Partial Differential Equations

The scale-invariant feature transform algorithm and its many variants are widely used in feature-based remote sensing image registration. However, it may be difficult to find enough correct correspondences for remote image pairs in some cases that exhibit a significant difference in intensity mapping. In this letter, a new gradient definition is introduced to overcome the difference of image intensity between the remote image pairs. Then, an enhanced feature matching method by combining the position, scale, and orientation of each keypoint is introduced to increase the number of correct correspondences. The proposed algorithm is tested on multispectral and multisensor remote sensing images. The experimental results show that the proposed method improves the matching performance compared with several state-of-the-art methods in terms of the number of correct correspondences and aligning accuracy.

Remote Sensing Image Registration With Modified SIFT and Enhanced Feature Matching

This paper presents a literature survey on existing disparity map algorithms. It focuses on four main stages of processing as proposed by Scharstein and Szeliski in a taxonomy and evaluation of dense two-frame stereo correspondence algorithms performed in 2002. To assist future researchers in developing their own stereo matching algorithms, a summary of the existing algorithms developed for every stage of processing is also provided. The survey also notes the implementation of previous software-based and hardware-based algorithms. Generally, the main processing module for a software-based implementation uses only a central processing unit. By contrast, a hardware-based implementation requires one or more additional processors for its processing module, such as graphical processing unit or a field programmable gate array. This literature survey also presents a method of qualitative measurement that is widely used by researchers in the area of stereo vision disparity mappings.

/pdf/literature-survey-on-stereo-vision-disparity-map-algorithms-3mtr9e2zyc.pdf

Literature Survey on Stereo Vision Disparity Map Algorithms

We present a comprehensive overview of the stereoscopic Intel RealSense RGBD imaging systems. We discuss these systems' mode-of-operation, functional behavior and include models of their expected performance, shortcomings, and limitations. We provide information about the systems' optical characteristics, their correlation algorithms, and how these properties can affect different applications, including 3D reconstruction and gesture recognition. Our discussion covers the Intel RealSense R200 and RS400.

Intel(R) RealSense(TM) Stereoscopic Depth Cameras

With the development of 3DTV, the conversion of existing 2D videos to 3D videos becomes an important component of 3D content production. One of the key steps in 2D to 3D conversion is how to generate a dense depth map. In this paper, we propose a novel depth extraction method based on motion and geometric information for 2D to 3D conversion, which consists of two major depth extraction modules, the depth from motion and depth from geometrical perspective. The H.264 motion estimation result is utilized and cooperates with moving object detection to diminish block effect and generates a motion-based depth map. On the other hand, a geometry-based depth map is generated by edge detection and Hough transform. Finally, the motion-based depth map and the geometry-based depth map are integrated into one depth map by a depth fusion algorithm.

A Depth Extraction Method Based on Motion and Geometry for 2D to 3D Conversion

A novel full-image guided filtering method is proposed. Different with many existing neighborhood filters, all input elements are employed during the proposed filtering approach. In addition, a novel scheme called weight propagation is proposed to compute support weights. It fulfills the requirements of edge preserving and low complexity. It is applied to the cost-volume filtering in the local stereo matching framework. The algorithm utilizing the proposed filtering method is currently one of the best local algorithms on the Middlebury stereo testbed in terms of both speed and accuracy.

Full-Image Guided Filtering for Fast Stereo Matching

The invention discloses a method for generating virtual multi-viewpoint images based on depth image layering, which comprises the following steps: (1) preprocessing depth images to be processed; (2) layering the preprocessed depth images so as to obtain layered depth images; (3) selecting depth layers focused by camera arrays, and determining prospect layers and background layers; (4) layering two dimensional images to be processed so as to obtain layered two dimensional images; (5) calculating valves of parallax errors corresponding to the two dimensional image layers corresponding to various depth layers; (6) expanding the layered two dimensional images so as to obtain expanded layered two dimensional images; (7) obtaining the virtual two-dimensional images of various virtual viewpoint positions by using a weighted level translation algorithm. By using the method of the invention, virtual multi-viewpoint images required by a multi-viewpoint auto-stereoscopic display system can be generated rapidly and effectively without parameters of a virtual multi-viewpoint camera array model, and the method has good fault-tolerant capacity to the input depth images.

Method for generating virtual multi-viewpoint images based on depth image layering

Natural image is an important source of human access to information, however observed image signals are often corrupted in the process of acquisition or transmission. As an important link of image preprocessing, image denoising has significant influence on the follow-up procedures. Unlike traditional methods that use related features of spatial or transform domain in a single image, we propose a deep learning method for natural image denoising. Our method directly learns an end-to-end mapping from a noisy image to a corresponding de-noised image. It's based on a deep convolutional architecture with rectified linear units and local response normalization. The experiment results show that the proposed deep convolutional architecture learns various features from noisy images, and achieves denoising results of high quality within short time for practical usage.

Deep convolutional architecture for natural image denoising

The invention discloses a method for converting 2D video into 3D video in a three-dimensional television system, which comprises the following steps: (1) obtaining a 2D video file to be converted, which is compressed by a video coding standard; (2) decoding to obtain original video, extracting the motion vector information of each 4*4 pixel block from a video decoder and converting the motion vector information into the motion amplitude; (3) describing an initial depth figure of each frame image by the motion amplitude; (4) iterating an edge correction filter wave to obtain a clear, accurate and dense depth figure of an object edge and finishing the expression of the 3D video. The invention obtains the initial depth figure by a middle result of the video decoder and well saves the processing time of signals and the cost of a final product; and an edge correction wave filter is designed so that the problem of obtaining the clear, accurate and dense depth figure of the object edge in analgorithm for obtaining depth based on an image is solved.

Lianghao Wang

Papers

A Depth Extraction Method Based on Motion and Geometry for 2D to 3D Conversion

Full-Image Guided Filtering for Fast Stereo Matching

Method for generating virtual multi-viewpoint images based on depth image layering

Deep convolutional architecture for natural image denoising

Method for converting 2D video into 3D video in three-dimensional television system