Quantum NeRF

Master's thesis on quantum implicit networks for novel view synthesis
Report bug · Request feature

Important

An example of an output 3D model, in PLY format, of our Q-NeRF model is available here. The presentation slides of this project's defense are also available in Google Slides.

Table of Contents

1. File Structure
2. Registering with Nerfstudio
3. Running Q-NeRF
4. License

File Structure

The project's file structure is organized as follows:

├── qnerf/
│   ├── modules/
│   │   ├── __init__.py
│   │   ├── modules.py   
│   ├── __init__.py
│   ├── qnerf.py
│   ├── qnerf_config.py
│   ├── qnerf_field.py
│   ├── ...
├── pyproject.toml

Registering with Nerfstudio

Ensure that nerfstudio has been installed according to the official installation instructions. Clone or fork this repository and run the commands:

conda activate nerfstudio
cd quantum-nerf/
pip install -e .
ns-install-cli

Running Q-NeRF

This repository creates a new Nerfstudio method named qnerf. To train with it, run the command:

ns-train qnerf --data [PATH]

License

Distributed under the Apache License. See LICENSE for more information.