论文标题
深斑视觉探针计
Deep Patch Visual Odometry
论文作者
论文摘要
我们提出了深层视觉探光仪（DPVO），这是一种新的单眼视觉探光度（VO）的深度学习系统。 DPVO使用一种新颖的经过反复的网络体系结构，旨在在跨时间跟踪图像贴片。通过使用深层网络来预测视频帧之间的密集流程，最近采用的VO方法可显着提高最新精度。但是，使用密集的流量会产生巨大的计算成本，从而使这些先前的方法在许多用例中都不切实际。尽管如此，已经假定密集流程很重要，因为它为不正确的匹配提供了额外的冗余。 DPVO反驳了这一假设，表明通过利用基于稀疏贴片的匹配而不是密集流的优势来获得最佳的准确性和效率。 DPVO引入了基于补丁的对应关系的新颖的经常性更新操作员，并与可区分的捆绑套件调整。在标准的基准测试上，DPVO的表现均优于所有先前的工作，包括基于学习的最先进的VO-System（DROID）使用三分之一的内存，而平均运行速度更快3倍。代码可从https://github.com/princeton-vl/dpvo获得。
We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO). DPVO uses a novel recurrent network architecture designed for tracking image patches across time. Recent approaches to VO have significantly improved the state-of-the-art accuracy by using deep networks to predict dense flow between video frames. However, using dense flow incurs a large computational cost, making these previous methods impractical for many use cases. Despite this, it has been assumed that dense flow is important as it provides additional redundancy against incorrect matches. DPVO disproves this assumption, showing that it is possible to get the best accuracy and efficiency by exploiting the advantages of sparse patch-based matching over dense flow. DPVO introduces a novel recurrent update operator for patch based correspondence coupled with differentiable bundle adjustment. On Standard benchmarks, DPVO outperforms all prior work, including the learning-based state-of-the-art VO-system (DROID) using a third of the memory while running 3x faster on average. Code is available at https://github.com/princeton-vl/DPVO
