相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Review
Computer Science, Hardware & Architecture
Sheng Shen et al.
Summary: Light field display (LFD) is a promising technology for reconstructing the light rays' distribution of real 3D scenes with all depth cues. Computer-generated content is widely used in LFD systems, providing rich 3D content. This paper introduces the applications of light field technologies in display systems, discusses virtual stereo content rendering techniques, and reviews coding and correction algorithms in virtual stereo content rendering techniques. New rendering algorithms are needed to solve the real-time light-field rendering problem for large-scale virtual scenes.
Article
Computer Science, Hardware & Architecture
Bangshao Fu et al.
Summary: In this paper, an analysis method for the relationship between light-field display (LFD) depth and 3D image definition is presented. A simplified analytical model suitable for standard LFD system is established, and the formula for calculating voxel size is derived in relation to the depth plane and viewing position. The analysis and experimental results contribute to a better understanding of the principle of light-field display and aid in the design and optimization of LFD systems for better display effect.
Editorial Material
Computer Science, Hardware & Architecture
Xiao Bai et al.
Article
Computer Science, Artificial Intelligence
Haotian Wang et al.
Summary: A method utilizing RGB-guided depth map recovery and a unified model to correct distorted boundaries is proposed in this paper. By extracting local structures and comparing similarities based on the SSIM index, erroneous regions in distorted depth maps are identified, leading to improved quality of recovered depth maps. The proposed method effectively corrects object boundaries and enhances the overall visual and quantitative qualities of depth map recovery.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Hardware & Architecture
Xiang Wang et al.
Summary: This paper provides a comprehensive review on recent deep learning methods for multi-view stereo, categorizing them into depth map based and volumetric based methods. It reviews representative methods in detail and summarizes widely used datasets and metrics for evaluation, while also presenting insightful observations and challenges for future research directions.
Article
Computer Science, Hardware & Architecture
Baoli Lu et al.
Summary: Stereo vision technology is crucial for three-dimensional reconstruction, but challenges exist in reconstructing moving objects due to image noise and motion blur. This article proposes a disparity optimization method based on depth change constraint, which improves reconstruction accuracy by eliminating mismatches and correcting disparity values.
Article
Computer Science, Hardware & Architecture
Henan Li et al.
Summary: The proposed approach utilizes SIFT and discrete viewpoint acquisition to correct perspective information and generate large-scale EIA, suitable for computational integral imaging and real scene acquisition, effectively reducing costs and workload.
Proceedings Paper
Computer Science, Artificial Intelligence
Huangying Zhan et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Article
Computer Science, Hardware & Architecture
Hyeongseok Kim et al.
Article
Computer Science, Software Engineering
Jia-Bin Huang et al.
ACM TRANSACTIONS ON GRAPHICS
(2014)
Article
Engineering, Electrical & Electronic
Hui Yuan et al.
IEEE TRANSACTIONS ON BROADCASTING
(2012)
Article
Engineering, Electrical & Electronic
Hui Yuan et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2011)
Article
Computer Science, Artificial Intelligence
A Criminisi et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2004)
