【CVPR2021】LoFTR: Detector-Free Local Feature Matching with Transformers

最新推荐文章于 2024-11-15 17:47:18 发布

Prettybritany

最新推荐文章于 2024-11-15 17:47:18 发布

阅读量1.3k

点赞数 29

分类专栏：图像配准论文阅读文章标签：算法计算机视觉图像处理 python 论文阅读

本文链接：https://blog.csdn.net/Prettybritany/article/details/136017333

版权

LoFTR: Detector-Free Local Feature Matching with Transformers

论文链接：LoFTR: Detector-Free Local Feature Matching with Transformers | IEEE Conference Publication | IEEE Xplore

代码：zju3dv/LoFTR: Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022 (github.com)

Abstract

We present a novel method for local image feature matching. Instead of performing image feature detection, description, and matching sequentially, we propose to first establish pixel-wise dense matches at a coarse level and later refine the good matches at a fine level. In contrast to dense methods that use a cost volume to search correspondences, we use self and cross attention layers in Transformer to obtain feature descriptors that are conditioned on both images. The global receptive field provided by Transformer enables our method to produce dense ma