Skip to content

lijiayu1125/hw02

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

作业2 复现schoenberger_phd_thesis Table 3.3: Results for our local feature benchmark. Fountain行

1.阅读INSTRUCTIONS.md并配置环境 准备数据

2.运行理解代码 scripts/matching_pipeline.m

3.运行理解代码 

scripts/reconstruction_pipeline.py

4.可视化论文图片结果

文件组成

SIFT

SIFT结果:

SIFT-PCA

SIFT-PCA遇到的问题:

1、

2、

SIFT-PCA结果:

DSP-SIFT

DSP-SIFT结果:

ConvOpt

opencv版本:

实现步骤:

1、先运行feature_extraction_convopt.py,获取描述子

2、在Matlab中注释调用描述子获取的程序,只运行匹配操作

ConvOpt结果:

TFeat

下载TFeat项目:GitHub - vbalnt/tfeat: TFeat descriptor models for BMVC 2016 paper "Learning local feature descriptors with triplets and shallow convolutional neural networks"

实现步骤:

1、先在Matlab中运行feature_extraction_tfeat.m,代码是检测每个图像中的关键点,并提取与这些关键点相关的图像补丁(patches),然后将这些补丁存储到文件中

2、再运行feature_extraction_tfeat.py,获取描述子

3、在Matlab运行匹配程序

TFeat结果:

LIFT

下载LIFT项目:GitHub - cvlab-epfl/LIFT: Code release for the ECCV 2016 paper

实现步骤:

1、编译c-code文件夹下的代码:

2、配置feature_extraction_list.sh路径

3、运行feature_extraction_lift.sh

4、运行feature_extraction_list.py,获取描述子

LIFT结果:

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published