{"id":18792523,"url":"https://github.com/prbonn/deep-point-map-compression","last_synced_at":"2025-06-30T06:32:50.309Z","repository":{"id":38349135,"uuid":"323385868","full_name":"PRBonn/deep-point-map-compression","owner":"PRBonn","description":null,"archived":false,"fork":false,"pushed_at":"2023-02-13T16:42:52.000Z","size":5212,"stargazers_count":95,"open_issues_count":3,"forks_count":28,"subscribers_count":11,"default_branch":"main","last_synced_at":"2025-04-13T14:47:11.852Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PRBonn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-12-21T16:08:58.000Z","updated_at":"2025-01-02T14:48:12.000Z","dependencies_parsed_at":"2024-11-07T21:33:57.909Z","dependency_job_id":null,"html_url":"https://github.com/PRBonn/deep-point-map-compression","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/PRBonn/deep-point-map-compression","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fdeep-point-map-compression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fdeep-point-map-compression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fdeep-point-map-compression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fdeep-point-map-compression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PRBonn","download_url":"https://codeload.github.com/PRBonn/deep-point-map-compression/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fdeep-point-map-compression/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262723806,"owners_count":23354118,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-07T21:20:21.199Z","updated_at":"2025-06-30T06:32:50.278Z","avatar_url":"https://github.com/PRBonn.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DEPOCO\n\nThis repository implements the algorithms described in our paper [Deep Compression for Dense Point Cloud Maps](https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/wiesmann2021ral.pdf).\n\n## How to get started (using Docker)\n\n### Dependenices nvida-docker\n\nInstall nvida-docker and follow [these](https://stackoverflow.com/a/61737404)\ninstructions\n\n## Data\nYou can download the dataset from [here](https://www.ipb.uni-bonn.de/html/projects/depoco/submaps.zip) and link the dataset to the docker container by configuring the Makefile\n\n```sh\nDATASETS=\u003cpath-to-your-data\u003e\n```\n\n## Building the docker container\n\nFor building the Docker Container simply run \n\n```sh\nmake build\n```\n\nin the root directory.\n\n## Running the Code\n\nThe first step is to run the docker container:\n\n```sh\nmake run\n```\n\nThe following commands assume to be run inside the docker container.\n\n### Training\n\nFor training a network we first have to create the config file with all the parameters.\nAn example of this can be found in `/depoco/config/depoco.yaml`. \nMake sure to give each config file a unique `experiment_id: ...` to not override previous models.\nTo train the network simply run\n\n```sh\npython3 trainer -cfg \u003cpath-to-your-config\u003e\n```\n\n### Evaluation\n\nEvaluating the network on the test set can be done by:\n\n```sh\npython3 evaluate.py -cfg \u003cpath-to-your-config\u003e\n```\n\nAll results will be saved in a dictonary.\n\n### Plotting the results\n\nWe can plot the quantitative results e.g. by using Jupyter-Lab.\nAn example of this is provided in `depoco/notebooks/visualize.ipynb`.\nJupyter-Lab can be started in the Docker container by:\n\n```sh\njupyter-lab  --ip 0.0.0.0 --no-browser --allow-root\n```\n\nThe 8888 port is forwarded which allows us to use it as if it would be on the host machine.\n\n### Pretrained models\n\nThe config files and the pretrained weights of our models are stored in `depoco/network_files/eX/`. The results can be inspected by the jupyter notebook `depoco/notebooks/visualize.ipynb`.\n\n## How to get started (without Docker)\n\n### Installation\n\nA list of all dependencies and install instructions can be derived from the Dockerfile.\n\n### Running the code\n\nAfter installation the training and evaluation can be run as explained before.\n\n### Qualitative Results\n\nPlotting the point clouds using open3d can be done by\n\n```sh\npyhon3 evaluate -cfg \u003cpath-to-your-config\u003e\n```\n\nThis can **not** be done in the docker container and thus requires the installation on the local machine.\n\n## Acknowledgements\n\nBig thanks to [Ignacio Vizzo](https://github.com/nachovizzo) for supporting me with Docker!\n\n## Citation\n\nIf you use this library for any academic work, please cite the original paper.\n\n```bibtex\n@article{wiesmann2021ral,\nauthor = {L. Wiesmann and A. Milioto and X. Chen and C. Stachniss and J. Behley},\ntitle = {{Deep Compression for Dense Point Cloud Maps}},\njournal = {IEEE Robotics and Automation Letters (RA-L)},\nvolume = 6,\nissue = 2,\npages = {2060-2067},\ndoi = {10.1109/LRA.2021.3059633},\nyear = 2021\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprbonn%2Fdeep-point-map-compression","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprbonn%2Fdeep-point-map-compression","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprbonn%2Fdeep-point-map-compression/lists"}