DeepMatching: Hierarchical Deformable Dense Matching
DeepMatching: Hierarchical Deformable Dense Matching
复制标题
DOI：
10.1007/s11263-016-0908-3
复制
发表时间：
2016-12-01
影响因子：
19.5
通讯作者：
Schmid, Cordelia
中科院分区：
文献类型：
--
作者：
Revaud, Jerome;Weinzaepfel, Philippe;Schmid, Cordelia
我们引入了一种新的匹配算法，称为深度匹配，以计算图像之间的密集对应。深度匹配依赖于为匹配图像而设计的分层、多层、相关架构，并受到深度卷积方法的启发。所提出的匹配算法可以处理非刚性变形和重复纹理，并在图像之间存在显著变化的情况下有效地确定密集对应。与最先进的匹配算法相比，我们在Mikolajczyk （Mikolajczyk et al.）上评估了深度匹配的性能。仿射区域探测器的比较，2005年),mpi - sinintel （Butler等）。用于光流评估的自然开源电影，2012)和Kitti （Geiger等人）。视觉与机器人：KITTI数据集，2013)数据集。DeepMatching优于最先进的算法，并在重复纹理方面显示出出色的结果。我们还将深度匹配应用于光流计算，称为DeepFlow，将其集成到Brox和Malik的大位移光流（LDOF）方法中（大位移光流：变分运动估计中的描述符匹配，2011）。该方法对大位移和复杂运动具有更强的鲁棒性。DeepFlow在光流估计的公共基准测试中获得了具有竞争力的性能。
We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images. DeepMatching relies on a hierarchical, multi-layer, correlational architecture designed for matching images and was inspired by deep convolutional approaches. The proposed matching algorithm can handle non-rigid deformations and repetitive textures and efficiently determines dense correspondences in the presence of significant changes between images. We evaluate the performance of DeepMatching, in comparison with state-of-the-art matching algorithms, on the Mikolajczyk (Mikolajczyk et al. A comparison of affine region detectors, 2005), the MPI-Sintel (Butler et al. A naturalistic open source movie for optical flow evaluation, 2012) and the Kitti (Geiger et al. Vision meets robotics: The KITTI dataset, 2013) datasets. DeepMatching outperforms the state-of-the-art algorithms and shows excellent results in particular for repetitive textures. We also apply DeepMatching to the computation of optical flow, called DeepFlow, by integrating it in the large displacement optical flow (LDOF) approach of Brox and Malik (Large displacement optical flow: descriptor matching in variational motion estimation, 2011). Additional robustness to large displacements and complex motion is obtained thanks to our matching approach. DeepFlow obtains competitive performance on public benchmarks for optical flow estimation.