计算机科学
稳健性(进化)
可扩展性
管道(软件)
由运动产生的结构
运动(物理)
计算机视觉
人工智能
迭代重建
钥匙(锁)
三维重建
完备性(序理论)
计算机图形学(图像)
数据挖掘
计算机工程
理论计算机科学
数据库
程序设计语言
数学
计算机安全
数学分析
基因
生物化学
化学
作者
Johannes L. Schönberger,Jan‐Michael Frahm
出处
期刊:Computer Vision and Pattern Recognition
日期:2016-06-01
被引量:3842
标识
DOI:10.1109/cvpr.2016.445
摘要
Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from unordered image collections. While incremental reconstruction systems have tremendously advanced in all regards, robustness, accuracy, completeness, and scalability remain the key problems towards building a truly general-purpose pipeline. We propose a new SfM technique that improves upon the state of the art to make a further step towards this ultimate goal. The full reconstruction pipeline is released to the public as an open-source implementation.
科研通智能强力驱动
Strongly Powered by AbleSci AI