用高效匹配摘要技术，让密集匹配的两视图估计快10-100倍。
Dense Match Summarization for Faster Two-view Estimation
- 提出匹配摘要方法，保留密集匹配精度的同时大幅减少数量。
- 在多个基准数据集上实现与全量匹配相当的精度，速度提升10-100倍。
- 适合需要快速鲁棒位姿估计的实时视觉系统开发者。
本文旨在加速基于密集对应关系的鲁棒两视图相对位姿估计。已有研究证明，密集匹配器能显著提升位姿估计的精度与鲁棒性，但其大量匹配点导致在RANSAC中进行鲁棒估计时计算耗时显著增加。为解决此问题，我们提出一种高效的匹配摘要方案，在保持与完整密集匹配相当精度的同时，实现10至100倍的运行速度提升。我们在标准基准数据集上，结合多种前沿密集匹配器验证了该方法的有效性。
原文摘要 · Abstract (English)
In this paper, we speed up robust two-view relative pose from dense correspondences. Previous work has shown that dense matchers can significantly improve both accuracy and robustness in the resulting pose. However, the large number of matches comes with a significantly increased runtime during robust estimation in RANSAC. To avoid this, we propose an efficient match summarization scheme which provides comparable accuracy to using the full set of dense matches, while having 10-100x faster runtime. We validate our approach on standard benchmark datasets together with multiple state-of-the-art dense matchers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。