Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 

Matchable Image Transformations for Long-term Visual Localization

System overview

Code to accompany our paper "Learning Maximally Matchable Image Transformations for Long-term Metric Visual Localization".

Dependencies

  • numpy
  • matplotlib
  • pytorch 1.1 + torchvision
  • Pillow
  • progress (for progress bars in train/val/test loops)
  • pyviso2 (included)
  • tensorboardX

Contents

  • run_vkitti.py - Top-level script for training and testing models using the Virtual KITTI dataset.
  • run_inthedark.py - Top-level script for training and testing models using the UTIAS In The Dark dataset.
  • matchability/ - Main codebase.
    • datasets/ - Modules for loading and pre-processing the Virtual KITTI and UTIAS In The Dark datasets for use with PyTorch.
    • experiment.py - General training, validation and testing loops.
    • models.py - Definitions for matcher proxy and image transformation models.
    • networks.py - General-purpose neural network classes, specialized in models.py.
    • options.py - Defines a container class to store configuration parameters and provides common defaults.
    • transforms.py - Custom image/tensor transformations.
    • utils.py - Miscellaneous utility functions.
  • scripts/ - Scripts for producing figures and videos used in the paper.

About

Learning Matchable Image Transformations

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages