| 本文已被：浏览 1971次 下载 2202次 |
码上扫一扫！ |
|
|
| 基于深度学习的多视图立体视觉综述 |
|
樊铭瑞1,2, 申冰可1,2, 牛文龙1,2, 彭晓东1,2,3, 谢文明1,2, 杨震1
|
|
1.中国科学院 国家空间科学中心, 北京 100190;2.中国科学院大学, 北京 100049;3.国科大杭州高等研究院, 浙江 杭州 310024
|
|
| 摘要: |
| 多视图立体视觉在自动驾驶、增强现实、遗产保护和生物医学等领域得到广泛应用. 为了弥补传统多视图立体视觉方法对低纹理区域不敏感、重建完整度差等不足, 基于深度学习的多视图立体视觉方法应运而生. 对基于深度学习的多视图立体视觉方法的开创性工作和发展现状进行综述, 重点关注基于深度学习的多视图立体视觉局部功能改进和整体架构改进方法, 深入分析代表性模型. 同时, 阐述目前广泛使用的数据集及评价指标, 并对比现有方法在数据集上的测试性能. 最后对多视图立体视觉未来有前景的研究发展方向进行展望. |
| 关键词: 深度学习 计算机视觉 三维重建 多视图立体视觉 |
| DOI：10.13328/j.cnki.jos.007248 |
| 分类号: |
| 基金项目:中国科学院基础前沿科学研究计划(22E0223301); 中国科学院青年创新促进会项目(E1213A02) |
|
| Survey on Multi-view Stereo Based on Deep Learning |
|
FAN Ming-Rui1,2, SHEN Bing-Ke1,2, NIU Wen-Long1,2, PENG Xiao-Dong1,2,3, XIE Wen-Ming1,2, YANG Zhen1
|
|
1.National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China;2.University of Chinese Academy of Sciences, Beijing 100049, China;3.Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
|
| Abstract: |
| Multi-view stereo (MVS) is widely used in fields such as autonomous driving, augmented reality, heritage conservation, and biomedicine. To address the limitations of traditional MVS methods, such as insensitivity to low-texture regions and poor reconstruction integrity, deep learning-based MVS methods have been proposed. This study reviews the pioneering work and current development of deep learning-based MVS methods. In particular, it focuses on methods for local functional improvement and overall architectural improvement and analyzes representative models. Meanwhile, the study describes widely used datasets and evaluation metrics and compares the test performance of existing methods on the datasets. Finally, promising research directions for MVS are presented. |
| Key words: deep learning computer vision 3D reconstruction multi-view stereo (MVS) |
