论文标题
lansac-flow：通用的两阶段图像对齐
RANSAC-Flow: generic two-stage image alignment
论文作者
论文摘要
本文考虑了两个图像之间密集对齐的通用问题，无论它们是视频的两个框架，两个截然不同的场景视图，两幅描述相似内容的绘画等。虽然每个这样的任务通常都使用域特异性解决方案来解决，但我们表明，简单的无人监督方法在整个任务范围内都表现出令人惊讶的范围。我们的主要见解是，参数和非参数比对具有互补的优势。我们提出了一个两个阶段的过程：首先，使用一个或多个同谱法，然后是非参数细像素对齐的基于特征的参数粗对齐。使用RANSAC在现成的深度功能上进行粗略对齐。通过深层网络以无监督的方式学习了细微的对齐方式，该网络优化了两个图像之间的标准结构相似性度量（SSIM），以及周期一致性。尽管它很简单，但我们的方法还是在一系列任务和数据集上显示出竞争性结果，包括对Kitti的无监督光流，HPATCHES上的密集通讯，对YFCC100M的两视图几何估计，Aachen Daynight上的本地化，以及第一次对Artworks of Artworks of Artworks of Brughel DataSet。我们的代码和数据可在http://imagine.enpc.fr/~shenx/ransac-flow/上找到
This paper considers the generic problem of dense alignment between two images, whether they be two frames of a video, two widely different views of a scene, two paintings depicting similar content, etc. Whereas each such task is typically addressed with a domain-specific solution, we show that a simple unsupervised approach performs surprisingly well across a range of tasks. Our main insight is that parametric and non-parametric alignment methods have complementary strengths. We propose a two-stage process: first, a feature-based parametric coarse alignment using one or more homographies, followed by non-parametric fine pixel-wise alignment. Coarse alignment is performed using RANSAC on off-the-shelf deep features. Fine alignment is learned in an unsupervised way by a deep network which optimizes a standard structural similarity metric (SSIM) between the two images, plus cycle-consistency. Despite its simplicity, our method shows competitive results on a range of tasks and datasets, including unsupervised optical flow on KITTI, dense correspondences on Hpatches, two-view geometry estimation on YFCC100M, localization on Aachen Day-Night, and, for the first time, fine alignment of artworks on the Brughel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/RANSAC-Flow/
