洪岩, 赵起, 曹越, 何超, 张聪炫, 陈震. 基于深度学习的双目立体匹配研究进展与分析[J]. 南昌航空大学学报(自然科学版), 2025, 39(1): 1-19, 107. DOI: 10.3969/j.issn.2096-8566.2025.01.001
引用本文: 洪岩, 赵起, 曹越, 何超, 张聪炫, 陈震. 基于深度学习的双目立体匹配研究进展与分析[J]. 南昌航空大学学报(自然科学版), 2025, 39(1): 1-19, 107. DOI: 10.3969/j.issn.2096-8566.2025.01.001
Yan HONG, Qi ZHAO, Yue CAO, Chao HE, Congxuan ZHANG, Zhen CHEN. Research Progress and Analysis of Stereo Matching Based on Deep Learning[J]. Journal of nanchang hangkong university(Natural science edition), 2025, 39(1): 1-19, 107. DOI: 10.3969/j.issn.2096-8566.2025.01.001
Citation: Yan HONG, Qi ZHAO, Yue CAO, Chao HE, Congxuan ZHANG, Zhen CHEN. Research Progress and Analysis of Stereo Matching Based on Deep Learning[J]. Journal of nanchang hangkong university(Natural science edition), 2025, 39(1): 1-19, 107. DOI: 10.3969/j.issn.2096-8566.2025.01.001

基于深度学习的双目立体匹配研究进展与分析

Research Progress and Analysis of Stereo Matching Based on Deep Learning

  • 摘要: 传统立体匹配算法通过匹配人工设计的特征描述来实现,但对遮挡、弱纹理及重复纹理及边缘等区域的计算效果并不理想。近年来,基于深度学习的立体匹配算法研究成为该领域的主流方向,且在算法性能及鲁棒性上均得到较大提升。为了系统梳理基于深度学习的立体匹配算法的研究现状与发展趋势,对立体匹配算法原理、传统立体匹配算法、基于深度学习的端到端及非端到端的立体匹配算法进行介绍,并对相关训练方法、损失函数及常用公开数据集进行总结,同时在常用数据集上对各类代表性算法进行对比分析,最后对立体匹配算法将面临的挑战和未来发展方向进行讨论。

     

    Abstract: Traditional stereo matching algorithms typically rely on matching of artificially crafted feature descriptors. Nevertheless, their performance in regions like occlusion, weak texture, repetitive texture, and edges leaves much to be desired. In recent years, deep learning-based stereo matching algorithms have emerged as a dominant approach, yielding significant improvements in both performance and robustness. In order to systematically organize the research status and development trends of deep - learning - based stereo matching algorithms, the research status and development trend of stereo matching algorithm based on deep learning, the principle of stereo matching algorithm, traditional stereo matching algorithm, end-to-end and non end-to-end stereo matching algorithm based on deep learning are introduced. Additionally, it comprehensively summarizes relevant training methods, loss functions, and commonly - used public datasets. Meanwhile, a comparative analysis of diverse representative algorithms is conducted on common datasets. Finally, the challenges and prospective development direction of stereo matching algorithm are discussed.

     

/

返回文章
返回