Skip to content

Latest commit

 

History

History

pytorch-superpoint

README.md

pytorch-superpoint

Input

  • img_A

Input

  • img_B

Input

(Image from http://icvl.ee.ic.ac.uk/vbalnt/hpatches/hpatches-sequences-release.tar.gz)

Output

  • Keypoints result

Output

  • Matches result (inliers)

Output

  • Matches result (outliers)

Output

  • Warping result (gray)

Output

  • Warping result (filterd)

Output

  • Warping result (correspondence)

Output

Usage

Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.

For the sample image,

$ python3 pytorch_superpoint.py

If you want to specify the input image, put the image path (as img_B) after the --input option, and the second image path (as img_A) after the --input2 option.

$ python3 pytorch_superpoint.py
 --input IMAGE_B --input2 IMAGE_A

Reference

Framework

Pytorch

Model Format

ONNX opset=11

Netron

SuperPointNet_gauss2.onnx.prototxt