$\mathbb{X}$解析对应网络
$\mathbb{X}$Resolution Correspondence Networks
摘要：
在本文中，我们的目标是建立准确的密集对应一对图像重叠的视野下具有挑战性的照明变化，视点的变化，风格的差异。通过对最先进的对应网络进行广泛的消融研究，我们惊讶地发现，广泛采用的4D相关张量及其相关的学习和处理模块可以去参数化并从训练中删除，对最终匹配精度的影响很小。禁用这些计算昂贵的模块可以大大加快训练过程，并允许使用4倍大的批量大小，这反过来又补偿了准确性下降。结合多GPU推理阶段，我们的方法有助于系统地研究从1280到4K的本地测试图像的匹配精度和上采样分辨率之间的关系。这导致发现的最佳分辨率$\mathbb{X}$，产生准确的匹配性能超过了国家的最先进的方法，特别是在较低的误差带上的公共基准建议的网络的存在。
英文摘要：
In this paper, we aim at establishing accurate dense correspondences between a pair of images with overlapping field of view under challenging illumination variation, viewpoint changes, and style differences. Through an extensive ablation study of the state-of-the-art correspondence networks, we surprisingly discovered that the widely adopted 4D correlation tensor and its related learning and processing modules could be de-parameterised and removed from training with merely a minor impact over the final matching accuracy. Disabling these computational expensive modules dramatically speeds up the training procedure and allows to use 4 times bigger batch size, which in turn compensates for the accuracy drop. Together with a multi-GPU inference stage, our method facilitates the systematic investigation of the relationship between matching accuracy and up-sampling resolution of the native testing images from 1280 to 4K. This leads to discovery of the existence of an optimal resolution $\mathbb{X}$ that produces accurate matching performance surpassing the state-of-the-art methods particularly over the lower error band on public benchmarks for the proposed network.
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。
