====== Structure-from-Motion ======

In this lab, we will experiment with 3D Structure-from-Motion systems, both feature-based and feed forward-based. More specifically, you will compare the performance of a state-of-the-art feature-based approach (Colmap) with a state-of-the-art feed forward-based approach (Depth Anything 3 (DA3)).


===== Download and installation =====

Pull the assignment template from [[https://raw.githubusercontent.com/tsattler/MPV_labs/refs/heads/main/3D_reconstruction_empty.ipynb|here]].

You can download required the data directly from the notebook or from [[https://github.com/tsattler/zurich_graffiti_dataset/raw/refs/heads/main/images.zip]]


===== The task =====

For this lab all explanations are contained in the corresponding [[https://raw.githubusercontent.com/tsattler/MPV_labs/refs/heads/main/3D_reconstruction_empty.ipynb|notebook]]. Please, refer to the notebook for details. 

<WRAP center round info>

To fulfil this assignment, you need to submit these files (all packed in one ''.zip'' file) into the [[https://cw.felk.cvut.cz/brute/|upload system]]:
  * **''results.html''** - Converted notebook. Transform your notebook ''3D_reconstruction_empty.ipynb'' into file results.html using ''jupyter nbconvert -–to html 3D_reconstruction_empty.ipynb -–EmbedImagesPreprocessor.resize=small -–output results.html''

</WRAP>


Your code and notebook will be checked manually.