【ICCV2021】COTR: Correspondence Transformer for Matching Across Images

原创

已于 2024-02-03 21:56:06 修改 · 1.2k 阅读

23 ·

CC 4.0 BY-SA版权

文章标签：

#transformer #深度学习 #人工智能 #图像处理

于 2024-02-03 21:53:09 首次发布

本文介绍了一种新颖的深度学习框架COTR，利用Transformer处理图像间对应问题，能同时处理稀疏和密集映射，通过多尺度推理提供高精度匹配。COTR在多个任务和数据集上表现出色，无需为特定任务重新训练，强调了可复现性和数据、代码的公开。

COTR: Correspondence Transformer for Matching Across Images

链接：COTR: Correspondence Transformer for Matching Across Images | IEEE Conference Publication | IEEE Xplore

Abstract

We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other. By doing so, one has the option to query only the points of interest and retrieve sparse correspondences, or to query all points in an image and obtain dense mappings. Importantly, in order to capture both local and global priors, and to let our model relate between image regions using the most relevant among said priors, we realize our network using a transformer. At inference time, we apply our correspondenc