rampvo
This is the official Pytorch implementation of the IROS 2024 paper Deep Visual Odometry with Events and Frames using Recurrent Asynchronous and Massively Parallel (RAMP) networks for Visual Odometry (VO).
File Explorer
Download Latest Version (.zip)- encoder.jpg
- overview.jpg
- MultiScale_Apollo.json
- MultiScale_ECCV20Competition.json
- MultiScale_EDS.json
- MultiScale_Malapert.json
- MultiScale_StereoDavis.json
- MultiScale_TartanEvent.json
- SingleScale_Apollo.json
- SingleScale_EDS.json
- SingleScale_Malapert.json
- SingleScale_StereoDavis.json
- default.yaml
- default_rgb.yaml
- default_StereoDavis.yaml
- fast.yaml
- precise.yaml
- __init__.py
- event_handle.py
- event_sequence.py
- events.py
- __init__.py
- correlation.cpp
- correlation.py
- correlation_kernel.cu
- __init__.py
- augmentation.py
- factory.py
- rgbd_utils.py
- RGBDDataset.py
- TartanEvent.py
- utils_data_readers.py
- __init__.py
- ba.cpp
- ba.py
- ba_cuda.cu
- block_e.cu
- block_e.cuh
- common.h
- dispatch.h
- lietorch_cpu.h
- lietorch_gpu.h
- rxso3.h
- se3.h
- sim3.h
- so3.h
- lietorch.cpp
- lietorch_cpu.cpp
- lietorch_gpu.cu
- __init__.py
- broadcasting.py
- gradcheck.py
- group_ops.py
- groups.py
- run_tests.py
- __init__.py
- BezierCurves.py
- pose_pred_utils.py
- __init__.py
- ba.py
- blocks.py
- config.py
- extractor.py
- logger.py
- net.py
- projective_ops.py
- Ramp_vo.py
- utils.py
- download_tartanevent.sh
- __init__.py
- eval_utils.py
- rotation_error_with_euler.py
- seed_everything.py
- transformers.py
- .gitignore
- environment.yml
- evaluate.py
- LICENSE
- README.md
- requirements.txt
- setup.py
- train.py
# Installation Guide
git clone https://github.com/uzh-rpg/rampvo
Downloads the entire project code from GitHub to your computer.
cd rampvo
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
Installs the package published on PyPI directly β no need to clone the source.
pip install .
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
Installs the package published on PyPI directly β no need to clone the source.
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
pip install .
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.