An unofficial Tensorflow implementation of the DSNT layer, as taken from the paper "Numerical Coordinate Regression with Convolutional Neural Networks".

Trained model and test code for high resolution optical and SAR image matching

Using Deep learning to locate the Synthetic Aperture Radar(SAR) images to the counterpart of Optical images.

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

Tensorflow prebuilt binary for Windows

Datasets, Transforms and Models specific to Computer Vision

This is an implementation of CVPR 2019 accepted paper "SOSNet: Second Order Similarity Regularization for Local Descriptor Learning" , and because of the training process was not public, I will try…

A Framework for Deep Learning-based Sparse SAR-Optical Image Matching

Pytorch implementation of "Fully-Convolutional Siamese Networks for Object Tracking"

Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"

HPatches: Homography-patches dataset.

Python & Matlab code for local feature descriptor evaluation with the HPatches dataset.

Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]

A Robust Matching Network for Gradually Estimating Geometric Transformation on Remote Sensing Imagery

Source code and datadset for "A Heterogeneous Remote-Sensing Image Matching Method Based on Deep Learning Feature"

Our "Visual Saliency Aided SAR and Optic Image Matching" papaer's code

Code and models for "Learning to Compare Image Patches via Convolutional Neural Networks"

Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]

Metric/Embedding learning using (convolutional) neural network with application to keypoint matching, stereo matching, image retrival, etc

http://torch.ch

H-Net: Neural Network for Cross-domain Image Patch Matching

Tensorflow implementation of both training and evaluation process of SiameseFC from Luca's paper: https://www.robots.ox.ac.uk/~luca/siamese-fc.html

reproduce paper PN-Net:Conjoined Triplet Deep Netwprk for Learning Local Image Descriptor

TS-Net: Combining Modality Specific and Common Features for Multimodal Patch Matching

[ICCV17] DeepCD: Learning Deep Complementary Descriptors for Patch Representations

Code and mode for CVPR 2017 paper "L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space"

Learning cross-spectral similarity measures with deep convolutional neural networks code

Patch Ordering based SAR Image Despeckling via Transform-Domain Filtering

Use torch in python for deep learning.