python实现sift-orb-surf等资料整理-一些cnn特征检测新算法-评估标准

http://www.cs.cornell.edu/courses/cs5670/2017sp/projects/pa2/index.html

http://www.cs.cornell.edu/courses/cs5670/2019sp/projects/pa2/index.html

http://www.cs.cornell.edu/courses/cs5670/2019sp

 

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/

 

https://www.robots.ox.ac.uk/~vgg/research/affine/det_eval_files/mikolajczyk_pami2004.pdf

 

 

https://github.com/JiawangBian/FM-Bench

更新:

Neural-Guided RANSAC 优于 RANSAC、USAC和Deep F-Mat等算法,现已开源!
From 海德堡大学

主页:Neural-Guided RANSAC - Visual Learning Lab Heidelb...

论文下载链接:[1905.04132] Neural-Guided RANSAC: Learning Where ...

代码:GitHub - vislearn/ngransac: Neural-Guided RANSAC f...

 

GLAMpoints:贪婪地学习准确的特征点匹配
《GLAMpoints: Greedily Learned Accurate Match points》
注:基于深度学习的特征点检测器 GLAMpoints,性能优于 SIFT等算法

每年还是有几篇用CNN做特征点检测或者匹配的论文,Ket.Net 性能优于SuperPoint和LF-Net等特征/关键点检测网络。From 帝国理工大学&Arraiy

arXiv:[1908.06812] GLAMpoints: Greedily Learned Accurate...

 

注:Ket.Net 性能优于SuperPoint和LF-Net等特征/关键点检测网络

论文下载链接:[1904.00889] Key.Net: Keypoint Detection by Handcr...

代码:GitHub - axelBarroso/Key.Net: Code for the ICCV19 ...

 

LCD 一种可学习的跨域描述符,能用于2D图像匹配和3D点云匹配,一举两得!2D优于 SIFT, SuperPoint; 3D优于PointNetAE。
From 新加坡科技设计大学&斯坦福大学&东京大学等 | AAAI 2020 (Oral)

论文下载链接:[1911.09326] LCD: Learned Cross-Domain Descriptors...

代码:GitHub - hkust-vgd/lcd: [AAAI'20] LCD: Learned Cro...

 

Super系列:SuperPoint+SuperGlue,也代表传统特征(点)检测、描述符和匹配方法逐渐在被深度学习方法代替,其性能优于NN、GMS等。From 苏黎世联邦理工学院 & Magic Leap

论文下载链接:[1911.11763] SuperGlue: Learning Feature Matching ...

 

 

 

 

其他:

https://blog.csdn.net/YunLaowang/article/details/85121235

立体视觉入门资料整理 

 评估:

https://gilscvblog.com/2015/11/07/performance-evaluation-of-binary-descriptor-introducing-the-latch-descriptor/

http://www.nlpr.ia.ac.cn/fanbin/Local%20Feature%20Descriptors_VALSE14.pptx

https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-5/47/2014/isprsarchives-XL-5-47-2014.pdf

https://www.researchgate.net/publication/328370491_A_Novel_Wide-Baseline_Stereo_Matching_Algorithm_Combining_MSER_and_DAISY

http://people.ucas.ac.cn/~bfan

樊彬

https://www.jiumodiary.com/ PDF搜索

Local Image Descriptor: Modern Approaches

http://www.nlpr.ia.ac.cn/fanbin/CVPR17Tutorial_LocalFeature.htm

http://www.nlpr.ia.ac.cn/fanbin/ACCV16Tutorial_LocalDescriptor.htm

http://epubs.surrey.ac.uk/812962/1/PhD-Thesis.pdf

Brown 数据集和评价指标HPatches 数据集和评价指标

https://blog.csdn.net/honyniu/category_8698831.html

[1] 基于角点的图像特征提取与匹配算法研究,薛金龙,2014.

[2] 基于局部特征的图像匹配与识别,宫明明,2014.

[3] 基于视觉信息的图像特征提取算法研究,戴金波,2014.

[4] 图像局部不变性特征与描述,王永明,王贵锦编著。

https://blog.csdn.net/zhaocj/category_2521441.html opencv源代码分析

https://blog.csdn.net/hujingshuang/category_9264206.html

https://blog.csdn.net/lhanchao/category_6430040.html

https://blog.csdn.net/aaron121211/category_6687444.html

https://blog.csdn.net/happyer88/article/details/46622657

https://blog.csdn.net/small_munich/category_7597772.html

 

CNN:

https://github.com/ducha-aiki

http://www.liuxiao.org/2018/10/deep-local-feature-%E6%96%87%E7%AB%A0%E6%94%B6%E9%9B%86/

https://www.epfl.ch/labs/cvlab/research/descriptors-and-keypoints/

http://cmp.felk.cvut.cz/wbs/

https://github.com/perdoch/hesaff

https://github.com/changkun/modern-cpp-tutorial

https://github.com/andyzeng/3dmatch-toolbox

https://github.com/jianxiongxiao/SFMedu

https://github.com/virtualgraham/L2-Net-Python-Keras

https://github.com/ducha-aiki/mods-light-zmq

https://github.com/DagnyT/hardnet

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

https://github.com/scape-research/SOSNet

https://github.com/yuruntian/SOSNet

https://github.com/uzh-rpg/imips_open

https://github.com/ahojnnes/local-feature-evaluation

https://github.com/axelBarroso/Key.Net 

https://github.com/zju3dv/GIFT

https://github.com/lzx551402/contextdesc

https://github.com/vcg-uvic/learned-correspondence-release

https://github.com/xuyanwu/RAL-Net

https://github.com/hpatches/hpatches-benchmark

https://github.com/hpatches/hpatches-dataset

https://github.com/vcg-uvic/lf-net-release

https://github.com/lzx551402/geodesc

https://github.com/rpautrat/SuperPoint

https://github.com/MagicLeapResearch/SuperPointPretrainedNetwork

https://github.com/cvlab-epfl/LIFT

https://github.com/yoshito-n-students/affine_invariant_features

https://github.com/zhengqili/MegaDepth

https://github.com/danini/homography-from-sift-features

https://github.com/zju3dv/pvnet

持续跟进这个人:https://github.com/cumtchenchang

https://github.com/ducha-aiki/pytorch-sift

https://github.com/Tommymhz/PointNet.PointNet2.PointSIFT.Pytorch

https://github.com/hmorimitsu/sift-flow-gpu

https://github.com/pitzer/SiftGPU

https://github.com/Celebrandil/CudaSift

https://github.com/pierrepaleo/sift_pyocl

https://github.com/amusi/SIFT-GPU

https://github.com/scanner-research/SiftGPU

 

https://github.com/withniu/GPU-SURF-/tree/master/SURFGPU-1.1.2

https://github.com/pablofdezalc/akaze

 

看了看国外课程,厉害。。。。。。

https://www.coursicle.com/gatech/courses/CS/

https://www.cc.gatech.edu/classes/AY2018/cs7643_fall/

 

CS 4476 Computer Vision

https://www.cc.gatech.edu/~zlv30/

https://www.cc.gatech.edu/~zlv30/courses/CS4476.html

https://www.cc.gatech.edu/~zlv30/courses/

https://www.cc.gatech.edu/~zlv30/courses/proj2.html

https://github.com/joshreno/CS4476

https://github.com/wtrimmer3/cs4476-computer-vision

https://github.com/huythong267/Computer-Vision-CS4476

https://samyak-268.github.io/F18CS4476/

https://github.com/keenborder786/CS-4476-Introduction-to-Computer-Vision-Udacity-Georgia-Tech-

https://github.com/brohand/SIFT-and-SVM-Image-Classifier

 

CS 6476 Computer Vision

https://www.cc.gatech.edu/~hays/compvision/  -----CS6476

https://www.cc.gatech.edu/~hays/compvision/

https://www.cc.gatech.edu/~hays/compvision2017/

https://www.cc.gatech.edu/~hays/compvision/proj2/

https://github.com/Helusen/CS6476-Computer-Vision-Projects

https://github.com/liuruoruo/CS6476-Computer-Vision

https://github.com/gravaman/cv_proj2

https://github.com/gravaman/cv_proj1

 

CSCI 1430 Computer Vision

http://cs.brown.edu/courses/csci1430/

https://github.com/mjl13/computer-vision-csci1430

https://github.com/sebastianbertoli/csci1430

https://github.com/AurekSkyclimber/IR_Magic_Final_Submission

 

还有其他资源:

https://github.com/rmislam/PythonSIFT

博客+代码:

https://medium.com/@lerner98/implementing-sift-in-python-36c619df7945

https://github.com/SamL98/PySIFT  

http://www.ipol.im/pub/art/2014/82/

http://www.ipol.im/pub/art/2014/82/sift_anatomy_20141201.zip 

http://www.vlfeat.org/overview/sift.html 

https://www.youtube.com/watch?v=mrVdGcvR8zo

https://www.youtube.com/watch?v=mrVdGcvR8zo

https://pythonawesome.com/an-implementation-of-the-sift-algorithm-in-cuda/

https://github.com/alicevision/popsift 

http://www.cs.cornell.edu/courses/cs4670/2015sp/projects/pa2/

http://www.cs.cornell.edu/courses/cs4670/2015sp/

http://www.cs.cornell.edu/courses/cs4670/2015sp/projects/pa3/

https://github.com/WangDequan/cs4670 

SURF:

https://github.com/luispedro/mahotas

https://mahotas.readthedocs.io/en/latest/surf.html
 

  • 1
    点赞
  • 17
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值