Image Matching: An Application-oriented Benchmark
关于Matlab代码中，使用的数据：
前两个是图像index，第三个是匹配对内点个数，后面的12个数构成4*3的pose姿态矩阵
关于姿态，我们得到了剔除后的匹配对，
已知相机内参，使用如下，求出Rt
cv::findEssentialMat()
cv::recoverPose()
数据：
http://www.robots.ox.ac.uk/~mobile/IJRR_2008_Dataset/data.html
https://github.com/opencv/opencv_contrib/pull/2383
LOGOS: Local Geometric Support for High-Outlier Spatial Verification
2018 IEEE International Conference on Robotics and Automation (ICRA)
https://github.com/short-circuitt/LOGOS
图像检索---哈希方法全集：
https://github.com/willard-yuan/hashing-baseline-for-image-retrieval
github搜索局部特征
https://github.com/topics/local-features?o=desc&s=stars
https://github.com/topics/image-matching
opencv例子:
https://github.com/opencv/opencv_extra/tree/master/testdata/cv/detectors_descriptors_evaluation
https://answers.opencv.org/question/1593/adding-a-new-detectordescriptor-to-evaluation-sample/
特征匹配数据集：CVPR2019的挑战：
https://image-matching-workshop.github.io/challenge/ https://www.visuallocalization.net/benchmark/
https://www.visuallocalization.net/ https://github.com/tsattler/visuallocalizationbenchmark
ICP资料；点匹配：
https://github.com/gwang-cv/Point-Set-Matching-Registration-Material
3D点云资料：
https://github.com/Yochengliu/awesome-point-cloud-analysis
局部描述符资料：
https://github.com/shamangary/awesome-local-global-descriptor
人脸资料：
https://github.com/ChanChiChoi/awesome-Face_Recognition
MatConvNet----------L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space -cvpr2017
https://github.com/yuruntian/L2-Net
作者其他相关：
http://gwang-cv.github.io/2018/10/28/Point%20Set%20Matching-Registration%20Benchmark/ 有代码
MatConvNet 1.0-beta18 or higher( http://www.vlfeat.org/matconvnet/).
https://tongtianta.site/paper/1922#anchor_78
https://www.cnblogs.com/eilearn/p/9998369.html
被引用：
https://xs.glgoo.99lb.net/scholar?cites=18331144065729754008&as_sdt=5,29&sciodt=0,29&hl=zh-CN
Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
https://github.com/wangzheallen/vsad
http://wangzheallen.github.io/
Repeatability is not enough: Learning affine regions via discriminability
https://github.com/ducha-aiki/affnet
Repeatability is not enough: Learning affine regions via discriminability
https://github.com/DagnyT/hardnet
https://github.com/empty16/hardnet.pytorch
Learning spread-out local feature descriptors
https://github.com/ColumbiaDVMM/Spread-out_Local_Feature_Descriptor
LF-Net: learning local features from images
https://github.com/vcg-uvic/lf-net-release
Geodesc: Learning local descriptors by integrating geometry constraints
https://github.com/lzx551402/geodesc
Human motion analysis with deep metric learnings
https://github.com/xrenaa/Human-Motion-Analysis-with-Deep-Metric-Learning
Learning deep descriptors with scale-aware triplet network
https://github.com/4uiiurz1/pytorch-scale-aware-triplet
Bingan: Learning compact binary descriptors with a regularized gan
https://github.com/maciejzieba/binGAN ---GAN的
Lmr: Learning a two-class classifier for mismatch removal
https://github.com/StaRainJ/LMR
mdBRIEF-a fast online-adaptable, distorted binary descriptor for real-time applications using calibrated wide-angle or fisheye cameras
https://github.com/urbste/mdBRIEF
A large dataset for improving patch matching
https://github.com/rmitra/PS-Dataset
Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks
https://github.com/kevinlin311tw/cvpr16-deepbit
Learning and matching multi-view descriptors for registration of point clouds
http://www.cse.ust.hk/~zluoag/ --大佬，还发了GeoDesc
https://github.com/zlthinker/RMBP
An evaluation of feature matchers forfundamental matrix estimation
https://github.com/JiawangBian/FM-Bench
TS-Net: combining modality specific and common features for multimodal patch matching
https://github.com/ensv/TS-Net
The perfect match: 3d point cloud matching with smoothed densities
https://github.com/zgojcic/3DSmoothNet
Multi-task structure-aware context modeling for robust keypoint-based object tracking
http://www.zhaoliming.net/research/keypoint
High-precision localization using ground texture
https://microgps.cs.princeton.edu/
ALIGNet: partial-shape agnostic alignment via unsupervised learning
https://github.com/ranahanocka/ALIGNet
Learning Local Descriptors with a CDF-Based Dynamic Soft Margin
https://github.com/lg-zhang/dynamic-soft-margin-pytorch
大佬的--有很多特征点论文，有代码：
Understanding and improving kernel local descriptors
http://cmp.felk.cvut.cz/~toliageo/publi.html
RF-Net: An End-to-End Image Matching Network based on Receptive Field
https://github.com/Xylon-Sean/rfnet
SOSNet: Second order similarity regularization for local descriptor learning
https://github.com/yuruntian/SOSNet
path数据：Leveraging outdoor webcams for local descriptor learning
https://github.com/pultarmi/AMOS_patches https://github.com/pultarmi/HardNet_MultiDataset
Beyond cartesian representations for local descriptors
https://github.com/cvlab-epfl/log-polar-descriptors
EE3-25 Deep Learning Coursework
https://www.miroslavgasparek.com/pdf/deep_learning_cw.pdf https://github.com/hsed/deeplearning-cw-2019
R2D2: Reliable and Repeatable Detector and Descriptor
Learning Local Descriptors by Optimizing the Keypoint-Correspondence Criterion: Applications to Face Matching, Learning from Unlabeled Videos and 3D-Shape Retrieval
https://github.com/nenadmarkus/wlrn
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
https://github.com/scape-research/SOSNet
LCD: Learned Cross-Domain Descriptors for 2D-3D Matching
https://github.com/hkust-vgd/lcd
GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
https://github.com/zju3dv/GIFT
H-Net: Neural Network for Cross-domain Image Patch Matching
https://github.com/Xylon-Sean/H-Net
MatchNet: Unifying Feature and Metric Learning for Patch
https://github.com/hanxf/matchnet
Cross-Spectral Image Patch Matching by Learning Features of the Spatially Connected Patches in a Shared Space
https://github.com/computervisionlearner/Image_matching
RPNet: an End-to-End Network for Relative Camera Pose Estimation
ContextDesc: Local Descriptor Augmentation with Cross-Modality Context
https://github.com/lzx551402/contextdesc
Learning to Compare Image Patches via Convolutional Neural Networks
https://github.com/szagoruyko/cvpr15deepcompare
MODS: Fast and Robust Method for Two-View Matching
Discriminative Learning of Deep Convolutional Feature Point Descriptors
https://github.com/etrulls/deepdesc-release
R2D2: Reliable and Repeatable Detector and Descriptor R2D2：可靠且可重复的特征点检测器和描述符
摘要：特征点/兴趣点检测和局部特征描述是许多计算机视觉应用程序中的基本步骤。经典方法基于“检测-然后描述”范式，其中使用单独的手工方法首先识别可重复的关键点，然后用局部描述符表示它们。经过度量学习损失训练的神经网络最近已经赶上了这些技术，重点是学习可重复的显著性图以进行关键点检测或在检测到的关键点位置学习描述符。在这项工作中，我们认为可重复的区域不一定是可区分的，因此可以导致选择次优的关键点。此外，我们主张仅应在可以高置信度执行匹配的区域中学习描述符。因此，我们建议共同学习关键点检测和描述，以及局部描述符判别力的预测因子。这样可以避免出现歧义区域，从而实现可靠的关键点检测和描述。我们的检测和描述方法可同时输出稀疏，可重复和可靠的关键点，其性能优于HPatches数据集和最近的亚琛Day-Night本地化基准测试中的最新检测器和描述符。
论文下载链接：https://europe.naverlabs.com/research/publications/r2d2-reliable-and-repeatable-detectors-and-descriptors-for-joint-sparse-local-keypoint-detection-and-feature-extraction/
代码：GitHub -https://github.com/naver/r2d2GLAMpoints: Greedily Learned Accurate Match points
https://arxiv.org/abs/1908.06812
Beyond Cartesian Representations for Local Descriptors 超越特征点局部描述子的笛卡尔表示
https://github.com/cvlab-epfl/log-polar-descriptors
https://arxiv.org/abs/1908.05547
综述：
Local feature descriptor for image matching: A Survey
http://www.arxiv-sanity.com/1811.10681
https://medium.com/@deepanshut041/introduction-to-feature-detection-and-matching-65e27179885d
https://github.com/ckddls1321/SLAM_Resources
MatConvNet----------Structure-from-Motion Using DenseCNN Features with Keypoint Relocalization
https://ipsjcva.springeropen.com/articles/10.1186/s41074-018-0042-y
http://www.ok.sc.e.titech.ac.jp/res/DenseSfM/index.html
https://github.com/resindraburiza/DenseSfMwithKeypointRelocalization
TILDE: A Temporally Invariant Learned DEtector -cvpr2015
https://github.com/vcg-uvic/TILDE
https://www.cnblogs.com/burton/p/10400834.html
HardNet 论文详解
知乎介绍：https://www.zhihu.com/question/28813777 计算机视觉入门书？
局部描述符论文总结，类似吕哥那种：
Local Features, Computation, Analysis
http://www.visionbib.com/bibliography/twod277lf1.html
Interest Operators, Interest Points, Feature Points, Salient Points
Scale Invariant Features, SIFT, SURF
http://www.visionbib.com/bibliography/twod277s1.html#Scale%20Invariant%20Features,%20SIFT,%20SURF
2D-3D：Three-Dimensional Matching Using Hashing/Indexing
http://www.visionbib.com/bibliography/match589.html#TT91511
Local Binary Patterns, LBP, Point Features
http://www.vlfeat.org/benchmarks/
https://github.com/vlfeat/vlbenchmarks
VLBenchmarks is a MATLAB framework for testing image feature detectors and descriptors. The latest version can be downloaded here.
References
1、K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. Van Gool. A comparison of affine region detectors. IJCV, 1(65):43–72, 2005.
2、H. Jegou, M. Douze, and C. Schmid. Exploiting descriptor distances for precise image search. Technical Report 7656, INRIA, 2011.
开源代码：
https://sites.google.com/site/uqchang/home/cv-code
http://rogerioferis.com/VisualRecognitionAndSearch2014/Resources.html
https://libraries.io/github/hpatches/hpatches-benchmark
https://www.cnblogs.com/Alliswell-WP/tag/%E7%BF%BB%E8%AF%91/
翻译工作：
Recent Advances in Features Extraction and Description Algorithms: A Comprehensive Survey——2017.03
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review001.html
HPatches A benchmark and evaluation of handcrafted and learned local descriptors——2017.04
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review002.html
A Performance Evaluation of Local Descriptors——2005.08
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review003.html
A survey of recent advances in visual feature detection—2014.08
A survey of recent advances in visual feature detection（Author's Accepted Manuscript）——2014.08
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review006.html
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review004.html
Local Invariant Feature Detectors: A Survey——2007.11
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review005.html
Evaluation of Interest Point Detectors
python-or-matlab实现特征点匹配Harris或SIFT
https://courses.cs.washington.edu/courses/cse576/06sp/projects/proj2-features/
https://courses.cs.washington.edu/courses/cse576/06sp/projects/proj2-features/index.html
https://www.cc.gatech.edu/classes/AY2016/cs4476_fall/results/proj2/html/alieberman3/
CSCI 1430: Introduction to Computer Vision
http://cs.brown.edu/courses/cs143/proj2/
https://blog.csdn.net/rain2211/article/details/53897389
https://blog.csdn.net/rain2211/category_6643826.html
A Comprehensive Performance Evaluation of 3D Local Feature Descriptors
http://www.escience.cn/system/download/71978
https://github.com/luisclaudio26/DescriptorsTestbench2.0
From handcrafted to deep local invariant features
https://arxiv.org/abs/1807.10254v1
https://arxiv.org/abs/1807.10254v2
https://arxiv.org/abs/1807.10254v3
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching
https://arxiv.org/pdf/1907.02890.pdf
HPatches: A benchmark and evaluation of handcrafted and learned local descriptors, Vassileios Balntas*, Karel Lenc*, Andrea Vedaldi and Krystian Mikolajczyk, CVPR 2017. *Authors contributed equally.
https://github.com/hpatches/hpatches-benchmark
https://github.com/hpatches/hpatches-dataset
改进：
https://github.com/abursuc/hbench
翻译：
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review002.html
总结：
https://github.com/unizard/RealFeature/blob/master/README.md
Evalation
- [Detector][Matlab] A comparison of affine region detectors, IJCV 2005, Oxford,
- [Descriptor][Matlab] A performance evaluation of local descriptors, PAMI 2005, Oxford
- [Binary] Comparative Evaluation of Binary Features, ECCV 2012, UNC
https://github.com/vcg-uvic/benchmark-orientation
https://www.epfl.ch/labs/cvlab/
https://www.epfl.ch/labs/cvlab/research/detect/orientation --无法打开
https://www.epfl.ch/labs/cvlab/research/descriptors-and-keypoints/research-detect-orientation/
https://www.epfl.ch/labs/cvlab/software/descriptors-and-keypoints/
https://www.epfl.ch/labs/cvlab/software/multi-view-stereo/
https://www.epfl.ch/labs/cvlab/software/surface/
Dataset and Codes
Datasets used in the paper.
Oxford and EF datasets in our software format
Codes for testing the learned orientation estimator
Github project page: https://github.com/cvlab-epfl/learn-orientation
Codes for the evaluation framework
Github project page: https://github.com/cvlab-epfl/benchmark-orientation
- [Matching] [Evaluation of Local Detectors and Descriptors for Fast Feature Matching, ICPR] (http://www.miksik.co.uk/papers/miksik2012icpr.pdf), Krystian Mikolajczyk
Evaluation of Local Detectors and Descriptors for Fast Feature Matching
A Comparative Study of Local Visual Descriptors
https://sites.cs.ucsb.edu/~holl/pubs/Gauglitz-2011-IJCV.pdf
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking
http://epubs.surrey.ac.uk/806146/1/miksik2012icpr.pdf
Evaluation of Local Detectors and Descriptors for Fast Feature Matching
https://arxiv.org/pdf/1710.06232.pdf
Analysis of Feature Detector and Descriptor Combinations with a Localization Experiment for Various Performance Metrics
http://legacydirs.umiacs.umd.edu/~hzhou/paper/zhou_ECCVW_2016.pdf
Evaluating Local Features for Day-Night Matching
https://www.cvg.ethz.ch/research/local-feature-evaluation/schoenberger2017comparative.pdf
http://www.cvg.ethz.ch/research/local-feature-evaluation/
https://github.com/ahojnnes/local-feature-evaluation
https://github.com/mihaidusmanu/local-feature-evaluation-vis
Comparative Evaluation of Hand-Crafted and Learned Local Features
https://www.robots.ox.ac.uk/~vgg/research/affine/det_eval_files/mikolajczyk_pami2004.pdf
翻译：
https://www.cnblogs.com/Alliswell-WP/p/TranslationOfPapers_Review003.html
https://www.zhihu.com/question/34556368?sort=created
A Performance Evaluation of Local Descriptors
图像特征点检测与匹配评价——量化
http://www.robots.ox.ac.uk/~vgg/research/affine/
Performance evaluation
1、K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir and L. Van Gool, A comparison of affine region detectors. In IJCV 65(1/2):43-72, 2005. PDF
2、K. Mikolajczyk, C. Schmid, A performance evaluation of local descriptors. In PAMI 27(10):1615-1630 . PDF
JiaWang Bian, Le Zhang, Yun Liu, Wen-Yan Lin, Ming-Ming Cheng, and Ian D. Reid. 2017. Image Matching: An Application-oriented Benchmark. arXiv:1709.03917 [cs]. Retrieved from http://arxiv.org/abs/1709.03917
https://arxiv.org/pdf/1709.03917v1.pdf
https://arxiv.org/abs/1709.03917v2
https://arxiv.org/abs/1709.03917v3
https://arxiv.org/pdf/1808.02267.pdf
https://github.com/skair39/Image-Matching-Benchmark
https://github.com/yuyou/MatchBench
https://github.com/yangninghua/MatchBench
https://github.com/JiawangBian/FM-Bench
https://github.com/lzx551402/contextdesc
https://github.com/lzx551402/geodesc
1480
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
