SuperPoint: Self-Supervised Interest Point Detection and Description

Code

• github.com/magicleap/SuperPointPretrainedNetwork
  Officialpytorch★ 0
• github.com/huggingface/transformers
  pytorch★ 158,292
• github.com/fabio-sim/LightGlue-ONNX
  pytorch★ 588
• github.com/borglab/gtsfm
  none★ 507
• github.com/ucuapps/openglue
  pytorch★ 362
• github.com/gabriel-sgama/semantic-superpoint
  pytorch★ 45
• github.com/tzvikif/SuperGlue
  pytorch★ 8
• github.com/AliYoussef97/SuperPoint-PrP
  pytorch★ 4
• github.com/Thomacdebabo/KP2Dtiny
  tf★ 1
• github.com/alekseychuiko/SuperPointMagic
  pytorch★ 0

Abstract

This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.

Tasks

Reproductions