双分辨率对应网络
Dual-Resolution Correspondence Networks
摘要：
我们解决了在一对图像之间建立密集像素对应关系的问题。在这项工作中，我们引入了双分辨率对应网络（DualRC-Net），以粗到细的方式获得像素对应。DualRC-Net提取粗分辨率和细分辨率特征图。粗糙的映射用于产生完整但粗糙的4D相关张量，然后通过可学习的邻域共识模块进行细化。精细分辨率的特征图被用来获得最终的密集的对应关系的指导下，细化的粗糙的4D相关张量。所选择的粗分辨率匹配分数允许细分辨率特征仅关注具有高置信度的有限数量的可能匹配。通过这种方式，DualRC-Net大大提高了匹配可靠性和定位精度，同时避免了在精细分辨率特征图上应用昂贵的4D卷积核。我们在大规模的公共基准测试中全面评估了我们的方法，包括HPatches，InLoc和Aachen Day-Night。它在所有这些方面都取得了最先进的成果。
英文摘要：
We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. DualRC-Net extracts both coarse- and fine- resolution feature maps. The coarse maps are used to produce a full but coarse 4D correlation tensor, which is then refined by a learnable neighbourhood consensus module. The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor. The selected coarse-resolution matching scores allow the fine-resolution features to focus only on a limited number of possible matches with high confidence. In this way, DualRC-Net dramatically increases matching reliability and localisation accuracy, while avoiding to apply the expensive 4D convolution kernels on fine-resolution feature maps. We comprehensively evaluate our method on large-scale public benchmarks including HPatches, InLoc, and Aachen Day-Night. It achieves the state-of-the-art results on all of them.
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。
