计算神经网络学习图像的仿射变换

Image Registration: From SIFT to Deep Learning - 知乎

 

不想太消极，但是Dosovitskiy的方法在实践中并没有真正起作用。它甚至没有经过适当的测试。
DeepHomography也是如此。
可以在实践中使用的深度检测器和描述符是：HardNet，SuperPoint和D2Net：请参阅最新和相关的CVPR研讨会
图像匹配：局部功能及其他
关于图像采样的内容：ASIFT和MODS。
关于医学图像注册：ANHIR-大挑战

很好的解释，但我将添加到Dmytro。
实际上，配准是在两个图像之间进行的，在这些图像中照明/噪声可能会发生变化。但是生成DeepHomography训练数据的过程没有考虑到这一点。
我建议检查提及的文件：Affnet和HardNet。

您没有讨论光流技术，这是一种出色的注册工具。例如，flownet。

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

https://arxiv.org/pdf/1709.03966.pdf

 

Deep Image Homography Estimation

https://blog.csdn.net/zcg1942/article/details/85254077

https://blog.csdn.net/ajing2014/article/details/53998866

https://arxiv.org/abs/1606.03798

https://github.com/yishiliuhuasheng/deep_image_homography_estimation

https://github.com/search?q=Deep+Image+Homography+Estimation

 

https://hal.archives-ouvertes.fr/hal-01859616/file/cnngeometric_pami.pdf

Convolutional neural network architecture for geometric matching

http://openaccess.thecvf.com/content_cvpr_2017/papers/Rocco_Convolutional_Neural_Network_CVPR_2017_paper.pdf

https://www.youtube.com/watch?v=4RMwGcT4uA8

Spatial Transformer Networks

https://blog.csdn.net/shaoxiaohu1/article/details/51809605

https://www.cnblogs.com/liaohuiqiang/p/9226335.html

https://blog.csdn.net/WZZ18191171661/article/details/100621925

https://zhuanlan.zhihu.com/p/43054073

 

Joint Multiple Image Parametric Transformation Estimation Via Convolutional Neural Networks

https://ieeexplore.ieee.org/document/8300522?denied=

 

Repeatability Is Not Enough: Learning Affine Regions via Discriminability

http://cmp.felk.cvut.cz/~radenfil/publications/Mishkin-ECCV18.pdf

https://github.com/ducha-aiki/affnet

 

 

谷歌学术搜索引用：

Convolutional neural network architecture for geometric matching

 

 

End-to-end weakly-supervised semantic alignment

http://openaccess.thecvf.com/content_cvpr_2018/papers/Rocco_End-to-End_Weakly-Supervised_Semantic_CVPR_2018_paper.pdf

 

SuperPoint: Self-Supervised Interest Point Detection and Description

 

http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w9/DeTone_SuperPoint_Self-Supervised_Interest_CVPR_2018_paper.pdf

 

Neighbourhood Consensus Networks

http://papers.nips.cc/paper/7437-neighbourhood-consensus-networks.pdf

http://papers.nips.cc/paper/7437-neighbourhood-consensus-networks

Deep Learning of Graph Matching

http://openaccess.thecvf.com/content_cvpr_2018/papers/Zanfir_Deep_Learning_of_CVPR_2018_paper.pdf

 

 

Deep Fundamental Matrix Estimation

http://openaccess.thecvf.com/content_ECCV_2018/papers/Rene_Ranftl_Deep_Fundamental_Matrix_ECCV_2018_paper.pdf

 

 

 

 

 

 

 

 

 

 

Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection

http://openaccess.thecvf.com/content_cvpr_2018/html/Novotny_Self-Supervised_Learning_of_CVPR_2018_paper.html

 

https://arxiv.org/pdf/1905.03561.pdf

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

https://github.com/AaltoVision/DGC-Net

Geometric Image Correspondence Verification by Dense Pixel Matching

http://openaccess.thecvf.com/content_WACV_2020/papers/Laskar_Geometric_Image_Correspondence_Verification_by_Dense_Pixel_Matching_WACV_2020_paper.pdf