https://github.com/cggos/semantic_feature_points

Semantic Feature Points: SuperPoint and GCNv2 feature points test
https://github.com/cggos/semantic_feature_points

deep-learning image-features semantic-slam

Last synced: about 2 months ago
JSON representation

Semantic Feature Points: SuperPoint and GCNv2 feature points test

• Host: GitHub
• URL: https://github.com/cggos/semantic_feature_points
• Owner: cggos
• Created: 2021-11-30T15:05:34.000Z (about 3 years ago)
• Default Branch: master
• Last Pushed: 2022-06-26T01:16:19.000Z (over 2 years ago)
• Last Synced: 2024-10-12T19:44:24.469Z (2 months ago)
• Topics: deep-learning, image-features, semantic-slam
• Language: C++
• Homepage:
• Size: 21.2 MB
• Stars: 26
• Watchers: 5
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Semantic Feature Points

* SuperPoint

* GCNv2 features

---

# Prerequisites

* OpenCV 3

* LibTorch

  - SuperPoint: LibTorch 1.2.0 `wget https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-1.2.0.zip`

  - GCNv2: LibTorch 1.10.0+cu102 (the latest)

# Build

```sh

cmake -B build [-D BUILD_SP=0 -D BUILD_GCN=1] # select one

cmake --build build -j4

```

# Run

```sh

./build/super_point

# or

./build/gcn_ftr

```



  

  



# Algorithms

## SuperPoint

Ref

* [magicleap/SuperPointPretrainedNetwork](https://github.com/magicleap/SuperPointPretrainedNetwork): SuperPoint Weights File and Demo Script

* [SuperPoint-SLAM](https://github.com/KinglittleQ/SuperPoint_SLAM)

* [open_vins_with_superpoint](https://github.com/robintzeng/open_vins_with_superpoint/tree/Superpoint)

## GCNv2 Feature

Ref

* [GCNv2 SLAM](https://github.com/jiexiong2016/GCNv2_SLAM)

* [Pytorch1.4下运行 GCNv2slam 需要修改的地方](https://blog.csdn.net/weixin_45650404/article/details/106085719)