arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11287cs.CV
收藏

用于密集跟踪的密集匹配器

Dense Matchers for Dense Tracking

Czech Technical University in Prague(布拉格捷克技术大学)

Tomáš Jelínek, Jonáš Šerých, Jiří Matas

AI总结:

本文扩展MFT框架,将对数间隔的多光流网络进行简单有效组合,证明其兼容性并超越单一网络性能,在位置预测精度上可与复杂非因果方法竞争,从而提升密集长期跟踪能力。

摘要:

光流是多种应用的有用输入,包括三维重建、姿态估计、跟踪和运动恢复结构。尽管光流具有实用性,但密集长期跟踪领域,尤其是宽基线条件下的密集长期跟踪,尚未得到广泛探索。本文扩展了MFT提出的在对数间隔区间上组合多个光流的概念。我们证明了MFT与不同光流网络的兼容性,所得到的结果超越了它们各自的单独性能。此外,我们提出了一种在MFT框架内对这些网络进行简单而有效的组合方法。该方法在位置预测精度方面被证明可与更复杂的非因果方法相竞争,凸显了MFT在增强长期跟踪应用方面的潜力。

英文摘要:

Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion. Despite its utility, the field of dense long-term tracking, especially over wide baselines, has not been extensively explored. This paper extends the concept of combining multiple optical flows over logarithmically spaced intervals as proposed by MFT. We demonstrate the compatibility of MFT with different optical flow networks, yielding results that surpass their individual performance. Moreover, we present a simple yet effective combination of these networks within the MFT framework. This approach proves to be competitive with more sophisticated, non-causal methods in terms of position prediction accuracy, highlighting the potential of MFT in enhancing long-term tracking applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑