This repository provides a framework to automate dataset preparation, perform partitioned or unified sparse reconstructions using COLMAP, and comparing alignment with ground truth camera poses. This code has been tested on 7-Scenes Dataset.
- Python 3.11 or 3.12
- COLMAP Binary Executable: The
colmapcommand must be mapped to your system's environmentalPATHvariables. Verify your installation by executing:
colmap -h
Initialize your virtual environment, isolate configuration parameters, and trigger the programmatic environment setup wrapper:
# Initialize native virtual environment
python -m venv venv
# Activate the isolated environment
# Windows (PowerShell):
.\venv\Scripts\Activate.ps1
# Linux / macOS (Bash):
source venv/bin/activate
# Execute automated module bootstrap setup
python pipeline.py setup --requirements requirements.txt