Skip to content

This is the repository for the Semantic SFM that is maintained for the 3D Vision course at ETH Zurich

Notifications You must be signed in to change notification settings

thearkamitra/3DVision_SemanticSFM

Repository files navigation

3DVision_SemanticSFM

1. Hloc

Make sure the Hloc repository and this repository are in the same directory. Make sure to install Hloc with all its dependencies. https://github.com/cvg/Hierarchical-Localization

2. Download the Dataset

Download the dataset into datasets/ and unzip it:

!wget http://cvg.ethz.ch/research/local-feature-evaluation/South-Building.zip -P datasets/
!unzip -q datasets/South-Building.zip -d datasets/

3. Ground Truth

Put the file ground_truth_adjusted.txt into the South-Building folder.

4. Segmentation

The overall method needs masks. The masks are stored as pkl file which can be generated from the segmentation model. You can download the weights that have been used from here: weights link. Once the masks are generated, put the masks folder into the South-Building path.

Pixellib BatchNormalization may not always show expected behaviour. Add the following line to the site package for semantic labelling incase the issue occurs: ''' from tensorflow.keras.layers import BatchNormalization '''

5. Notebook

Open the Jupyter Notebook to run the code.

About

This is the repository for the Semantic SFM that is maintained for the 3D Vision course at ETH Zurich

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published