{"id":24605482,"url":"https://github.com/donghwijung/lorcon-lo","last_synced_at":"2025-05-05T16:44:55.901Z","repository":{"id":189561742,"uuid":"468313893","full_name":"donghwijung/LoRCoN-LO","owner":"donghwijung","description":"LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry","archived":false,"fork":false,"pushed_at":"2024-07-04T05:13:11.000Z","size":39,"stargazers_count":17,"open_issues_count":0,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-30T22:32:07.401Z","etag":null,"topics":["deep-learning","lcrn","lidar-odometry","paper","rellis-3d","robotics"],"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/donghwijung.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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}},"created_at":"2022-03-10T11:28:08.000Z","updated_at":"2025-03-08T08:17:42.000Z","dependencies_parsed_at":"2024-01-07T20:55:00.204Z","dependency_job_id":null,"html_url":"https://github.com/donghwijung/LoRCoN-LO","commit_stats":null,"previous_names":["donghwijung/lorcon-lo"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/donghwijung%2FLoRCoN-LO","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/donghwijung%2FLoRCoN-LO/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/donghwijung%2FLoRCoN-LO/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/donghwijung%2FLoRCoN-LO/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/donghwijung","download_url":"https://codeload.github.com/donghwijung/LoRCoN-LO/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252535493,"owners_count":21763965,"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":["deep-learning","lcrn","lidar-odometry","paper","rellis-3d","robotics"],"created_at":"2025-01-24T16:17:41.526Z","updated_at":"2025-05-05T16:44:55.884Z","avatar_url":"https://github.com/donghwijung.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# \u003cimg src=\"https://user-images.githubusercontent.com/73815549/157867543-bc994b16-5dda-4e30-bcff-55c522c91f50.png\" width=75/\u003e LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry\nVideo [[link]](https://youtu.be/_Ld58Rn_y-s) Paper [[link]](https://arxiv.org/pdf/2303.11853.pdf)\n## Download datasets\nKITTI dataset (http://www.cvlibs.net/datasets/kitti/eval_odometry.php).\n- velodyne laser data, calibration files, ground truth poses\n\nRellis-3D dataset (https://github.com/unmannedlab/RELLIS-3D).\n- SemanticKITTI Format, Scan Poses files\n\n## Setup directories\n```bash\nbash setup_directories.sh\n```\nEnter dataset name\n```\nKITTI # KITTI dataset\nRellis-3D # Rellis-3D dataset\n```\n\n## Move datasets\n### KITTI\nMove calib files (from 00 to 10)\n```bash\nmv data_odometry_calib/dataset/sequences/00/calib.txt data/KITTI/calib/00.txt\n```\nMove pose files (from 00 to 10)\n```bash\nmv data_odometry_poses/dataset/poses/00.txt data/KITTI/pose/00.txt\n```\nMove scan files (from 00 to 10)\n```bash\nmv data_odometry_velodyne/dataset/sequences/00/velodyne data/KITTI/scan/00/\n```\n\n### Rellis-3D\nMove pose files (from 00 to 04)\n```bash\nmv Rellis_3D_lidar_poses_20210614/Rellis_3D/000000/poses.txt data/Rellis-3D/pose/00.txt\n```\nMove scan files (from 00 to 04)\n```bash\nmv Rellis_3D_os1_cloud_node_kitti_bin/Rellis_3D/000000/os1_cloud_node_kitti_bin data/Rellis-3D/scan/00/\n```\n\n## Setup the environment\n```bash\nconda create -n LoRCoN-LO python=3.8\nconda activate LoRCoN-LO\npip install -r requirements.txt\n```\n\n## Change the config file\nChange the config file (`config/config.yaml`) depending on your directory configuration.\n\n## Pre-process\n- transform ground truth poses from cam to vel\n```bash\npython preprocess/transform_poses_cam_to_vel.py\n```\n\n## Compute relative poses\n```bash\npython preprocess/relative_pose_calculator.py\n```\n\n## Generate input data\n```bash\npython preprocess/gen_data.py\n```\n\n## Train and Test\n```bash\npython train.py\npython test.py\n```\n\n## Pre-trained models\nKITTI model wass trained with 00 to 08 sequences.\n\n- [Download](https://drive.google.com/file/d/1pw8I5LrH5BI5_Oo8G7rhdiXX-vJlauIi/view?usp=sharing)\n\nRellis-3D model was trained with 00 to 03 sequences.\n\n- [Download](https://drive.google.com/file/d/1edg5MsBRWxS7Q-slpvR3zbS8mIroLTUB/view?usp=sharing)\n\nWhen downloading and running the model, please modify the checkpoint related code in `confg/config.yaml`.\n\n## Paper\n```\n@inproceedings{jung2023lorcon,\n  title={LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry},\n  author={Jung, Donghwi and Cho, Jae-Kyung and Jung, Younghwa and Shin, Soohyun and Kim, Seong-Woo},\n  booktitle={2023 International Conference on Electronics, Information, and Communication (ICEIC)},\n  pages={1--4},\n  year={2023},\n  organization={IEEE}\n}\n```\n\n## Acknowledgement\nThe input data generation module is adapted from [Overlapnet](https://github.com/PRBonn/OverlapNet).\n\n## License\n\nCopyright 2022, Donghwi Jung, Jae-Kyung Cho, Younghwa Jung, Soohyun Shin, Seong-Woo Kim, Autonomous Robot Intelligence Lab, Seoul National University.\n\nThis project is free software made available under the MIT License. For details see the LICENSE file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdonghwijung%2Florcon-lo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdonghwijung%2Florcon-lo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdonghwijung%2Florcon-lo/lists"}