{"id":18792522,"url":"https://github.com/prbonn/kppr","last_synced_at":"2025-09-21T17:29:06.959Z","repository":{"id":65604635,"uuid":"575349174","full_name":"PRBonn/kppr","owner":"PRBonn","description":"KPPR: Exploiting Momentum Contrast for Point Cloud-Based Place Recognition","archived":false,"fork":false,"pushed_at":"2023-03-08T14:06:59.000Z","size":20,"stargazers_count":22,"open_issues_count":0,"forks_count":0,"subscribers_count":5,"default_branch":"main","last_synced_at":"2023-08-10T20:33:27.707Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-12-07T10:06:47.000Z","updated_at":"2023-06-30T01:21:42.000Z","dependencies_parsed_at":"2023-01-31T11:35:18.295Z","dependency_job_id":null,"html_url":"https://github.com/PRBonn/kppr","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fkppr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fkppr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fkppr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PRBonn%2Fkppr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PRBonn","download_url":"https://codeload.github.com/PRBonn/kppr/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223589801,"owners_count":17170038,"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":"2024-11-07T21:20:20.959Z","updated_at":"2025-09-21T17:29:01.933Z","avatar_url":"https://github.com/PRBonn.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# KPPR: Exploiting Momentum Contrast for Point Cloud-Based Place Recognition\n\n## Installation\n\n1. Install all requirements: `pip install -r requirements.txt`\n2. Install this repository: `pip install -e .`\n\n## Usage\n\n### Training\n\nAll the following commands should be run in `kppr/`\n\n- Please update the config files (especially the `oxford_data.yaml` to match your data_dir)\n- Run the training: `python train.py`\n- The output will be saved in `retriever/experiments/{EXPERIMENT_ID}`\n\n### Testing\n\n- Test the model by running: `python test.py --checkpoint {PATH/TO/CHECKPOINT.ckpt} --dataset {DATASET} --base_dir {PATH/TO/DATA}`, where `{DATASET}` is e.g. `oxford`\n- The output will be saved in the same folder as the checkpoint\n- All the results can be visualized with: `python scripts/vis_results.py`\n- The numbers of the paper are in `experiments/kppr/.../oxford_evaluation_query.txt`\n- The pre-trained model can be downloaded [here](https://www.ipb.uni-bonn.de/html/projects/kppr/kppr.ckpt) and should be placed into `experiments/kppr/lightning_logs/version_0/`.\n\n## Data\n\n- The pre-compressed point cloud maps can be downloaded [here](https://www.ipb.uni-bonn.de/html/projects/retriever/oxford_compressed.zip) and should be extracted to `data/` (or simply put a symbolic link).\n- For the uncompressed point clouds, I refer to [PointNetVLAD](https://github.com/mikacuy/pointnetvlad).\n\n## Citation\n\nIf you use this library for any academic work, please cite the original paper.\n\n```bibtex\n@article{wiesmann2023ral,\nauthor = {L. Wiesmann and L. Nunes and J. Behley and C. Stachniss},\ntitle = {{KPPR: Exploiting Momentum Contrast for Point Cloud-Based Place Recognition}},\njournal = ral,\nvolume = {8},\nnumber = {2},\npages = {592-599},\nyear = 2023,\nissn = {2377-3766},\ndoi = {10.1109/LRA.2022.3228174},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprbonn%2Fkppr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprbonn%2Fkppr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprbonn%2Fkppr/lists"}