RANSAC-Flow: generic two-stage image alignment
RANSAC-Flow: generic two-stage image alignment
复制标题
DOI：
10.1007/978-3-030-58548-8_36
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
XI Shen;Franccois Darmon;Alexei A. Efros;Mathieu Aubry
中科院分区：
文献类型：
--
作者：
XI Shen;Franccois Darmon;Alexei A. Efros;Mathieu Aubry
本文考虑了两个图像之间密集对齐的一般问题，无论它们是视频的两个帧、场景的两个截然不同的视图、描绘相似内容的两幅画等。虽然每个此类任务通常都是通过特定领域的解决方案来解决的，但我们表明，简单的无监督方法在一系列任务中表现得令人惊讶地好。我们的主要见解是参数和非参数对齐方法具有互补的优势。我们提出了一个两阶段的过程：首先，使用一个或多个单应性进行基于特征的参数粗对齐，然后是非参数精细像素对齐。使用 RANSAC 对现成的深度特征进行粗对齐。精细对齐是通过深度网络以无监督的方式学习的，该网络优化了两个图像之间的标准结构相似性度量（SSIM）以及循环一致性。尽管很简单，我们的方法在一系列任务和数据集上显示出有竞争力的结果，包括 KITTI 上的无监督光流、Hpatches 上的密集对应、YFCC100M 上的双视图几何估计、Aachen Day-Night 上的定位，以及首次在 Brughel 数据集上对艺术品进行精细对齐。我们的代码和数据可在 http://imagine.enpc.fr/~shenx/RANSAC-Flow/ 获取。
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 onKITTI, dense correspondences onHpatches, two-view geometry estimation onYFCC100M, localization onAachen Day-Night, and, for the first time, fine alignment of artworks on theBrughel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/RANSAC-Flow/ .