Mini-DPVO

A miniature version of DPVO. Using Rerun viewer, Pixi and Gradio for easy use

Installation

Easily installable via Pixi.

git clone https://github.com/pablovela5620/mini-dpvo.git
cd mini-dpvo
pixi install
pixi run post-install

Recent Update Notes

• mini-dpvo now uses the prebuilt lietorch package from Pixi instead of building the vendored copy in-tree.
• lietorch is ABI-coupled to the exact PyTorch/libtorch build. If pixi upgrades pytorch without a matching lietorch build, imports will fail with undefined-symbol errors from lietorch_backends.
• The current working combination is driven by pyproject.toml/pixi.lock; avoid changing pytorch, libtorch, torchvision, or lietorch independently.
• torch_scatter was intentionally removed from the runtime dependency set and replaced with local scatter helpers implemented with native PyTorch ops in mini_dpvo/scatter_utils.py.
• This was not a cleanup preference. It was a compatibility decision required to move mini-dpvo onto the newer PyTorch/CUDA stack needed by the prebuilt lietorch package and the current 5090-tested environment.
• In practice: reintroducing torch_scatter means re-checking wheel availability and ABI compatibility against the exact pytorch/libtorch/CUDA combination in this repo. Do not assume a PyPI or PyG wheel will be compatible just because it exists for a nearby Torch/CUDA version.
• That torch_scatter replacement is a narrow compatibility workaround for the current app/demo path and has not been broadly validated outside this workflow yet.
• The package still builds its own CUDA extensions (mini_dpvo._cuda_corr and mini_dpvo._cuda_ba) locally through pixi run post-install.
• Example assets and checkpoints are now fetched through hf download, not huggingface-cli.
• pixi run demo has been validated on an RTX 5090 with the current lockfile.
• pixi run rerun and GUI flows require a valid display session. In headless shells, Rerun will fail unless DISPLAY/XAUTHORITY are set.

Demo

Hosted Demos can be found in either lightning studio or huggingface spaces

To run the gradio frontend

pixi run app

To run using just the rerun visualizer

pixi run rerun

To run the full demo pipeline

pixi run demo

look in the pixi.toml file to see exactly what each command does under tasks

Acknowledgements

Original Code and paper from DPVO

@article{teed2023deep,
  title={Deep Patch Visual Odometry},
  author={Teed, Zachary and Lipson, Lahav and Deng, Jia},
  journal={Advances in Neural Information Processing Systems},
  year={2023}
}