期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 35, 期 12, 页码 2841-2853出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2012.218
关键词
Structure from motion; 3D reconstruction; Markov random fields; belief propagation
资金
- US National Science Foundation [IIS-0705774, IIS-0964027]
- Indiana University Data to Insight Center
- Lilly Endowment
- Quanta Computer
- MIT Lincoln Labs
- Intel Corp.
- NSF [EIA-0202048]
- IBM
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1149393] Funding Source: National Science Foundation
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1253549] Funding Source: National Science Foundation
Recent work in structure from motion (SfM) has built 3D models from large collections of images downloaded from the Internet. Many approaches to this problem use incremental algorithms that solve progressively larger bundle adjustment problems. These incremental techniques scale poorly as the image collection grows, and can suffer from drift or local minima. We present an alternative framework for SfM based on finding a coarse initial solution using hybrid discrete-continuous optimization and then improving that solution using bundle adjustment. The initial optimization step uses a discrete Markov random field (MRF) formulation, coupled with a continuous Levenberg-Marquardt refinement. The formulation naturally incorporates various sources of information about both the cameras and points, including noisy geotags and vanishing point (VP) estimates. We test our method on several large-scale photo collections, including one with measured camera positions, and show that it produces models that are similar to or better than those produced by incremental bundle adjustment, but more robustly and in a fraction of the time.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据