{"id":18828572,"url":"https://github.com/jmuwrobotics/libbicos","last_synced_at":"2025-10-14T08:06:31.808Z","repository":{"id":261661922,"uuid":"858646904","full_name":"JMUWRobotics/libBICOS","owner":"JMUWRobotics","description":"GPU-Accelerated Binary Correspondence Search for Multishot Stereo Vision","archived":false,"fork":false,"pushed_at":"2025-06-06T11:42:35.000Z","size":368864,"stargazers_count":5,"open_issues_count":1,"forks_count":2,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-10-14T08:06:25.271Z","etag":null,"topics":["computer-vision","cuda","depth-map","stereo-camera","stereo-matching","stereo-vision"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JMUWRobotics.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING","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,"zenodo":null}},"created_at":"2024-09-17T09:30:58.000Z","updated_at":"2025-06-10T23:58:32.000Z","dependencies_parsed_at":"2025-06-09T01:14:01.349Z","dependency_job_id":null,"html_url":"https://github.com/JMUWRobotics/libBICOS","commit_stats":null,"previous_names":["jmuwrobotics/libbicos"],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/JMUWRobotics/libBICOS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JMUWRobotics%2FlibBICOS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JMUWRobotics%2FlibBICOS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JMUWRobotics%2FlibBICOS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JMUWRobotics%2FlibBICOS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JMUWRobotics","download_url":"https://codeload.github.com/JMUWRobotics/libBICOS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JMUWRobotics%2FlibBICOS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279018303,"owners_count":26086333,"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","status":"online","status_checked_at":"2025-10-14T02:00:06.444Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["computer-vision","cuda","depth-map","stereo-camera","stereo-matching","stereo-vision"],"created_at":"2024-11-08T01:31:38.014Z","updated_at":"2025-10-14T08:06:31.800Z","avatar_url":"https://github.com/JMUWRobotics.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# libBICOS\n\nBInary COrrespondence Search for multi-shot stereo imaging, with optional CUDA acceleration.\n\n## Citing:\n\nThis is the implementation of the [corresponding paper](https://isprs-archives.copernicus.org/articles/XLVIII-2-W7-2024/57/2024/isprs-archives-XLVIII-2-W7-2024-57-2024.pdf) which appeared in [Optical 3D Metrology 2024](https://o3dm.fbk.eu):\n```bibtex\n@article{liebender2024libbicos,\n  title={libBICOS -- An Open Source GPU-Accelerated Library implementing BInary COrrespondence Search for 3D Reconstruction},\n  author={Liebender, Christoph and Bleier, Michael and N{\\\"u}chter, Andreas},\n  journal={The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},\n  volume={48},\n  pages={57--64},\n  year={2024},\n  publisher={Copernicus Publications G{\\\"o}ttingen, Germany}\n}\n```\n\n## Build:\n\nDependencies:\n\n- `gcc` or equivalent C compiler with C++17 support (build)\n- [`meson`](https://github.com/mesonbuild/meson) \u003e= 1.1.0 (build)\n- `opencv 4.x` with cuda support\n- `cuda 12.x` including toolkit\n- [`cog`](https://pypi.org/project/cogapp/) (build, cuda, for generating sources)\n- [`benchmark`](https://github.com/google/benchmark) (optional, for executing benchmarks)\n\n```bash\n# recommended: clone the most recent release\n$ git clone --depth 1 --branch v2.2.0 https://github.com/JMUWRobotics/libBICOS\n$ cd libBICOS\n\n$ meson setup builddir --buildtype release\n\n# optional but recommended if you have access to a CUDA-capable GPU\n$ meson configure -Dimplementation=cuda builddir\n\n$ meson install -C builddir\n```\n\nThe versioning scheme of the library is [Semantic Versioning](https://semver.org/).\n\n## Usage\n\n### Linking\nAfter installing, you can include `/usr/local/include/BICOS/*` and link against `/usr/local/lib/libBICOS.so`.\n\n### Python module\nWith an available python installation, meson will build a (somewhat experimental) python module `pybicos`. It is a wrapper around the C++ API for more convenient experimentation:\n```python\nimport pybicos\nimport cv2 as cv\n\nlstack = [cv.imread(f\"data/left/{i}.png\", cv.IMREAD_UNCHANGED) for i in range(20)]\nrstack = [cv.imread(f\"data/right/{i}.png\", cv.IMREAD_UNCHANGED) for i in range(20)]\n\ncfg = pybicos.Config()\ncfg.nxcorr_threshold = 0.9\n\ndisparity, correlation_map = pybicos.match(lstack, rstack, cfg)\n\n```\n\n### Commandline-interface\nAlternatively, this project builds `bicos-cli`. To give you a feel for the parameters of BICOS, you can download an example dataset with [`data/prepare.sh`](/data/prepare.sh) that contains rectified imagery from a stereo camera, where images per side only differ in the projected light pattern.\nCalling:\n```console\n$ bicos-cli data/{left,right} -q data/Q.yaml --threshold 0.96 --stacksize 33 --limited --variance 2.0 --step 0.1 -o /tmp/result.png\n```\nwill get you:\n\n#### Disparity\n![Example disparity](/example-disp.png)\n\n#### Pointcloud\n![Example pointcloud](/example-pcl.png)\n\nWhile only requiring ~44ms (RTX4090) and ~1.6GB VRAM for matching on two stacks of 33 images each.\n\nThe most significant parameters can be summarized:\n\n- `--threshold`: increasing this reduces match-outliers. High values rely on a reliable pattern.\n- `--variance`: high values reduce coarse outliers, e.g. pixels where no pattern was projected. May reduce correct matches on low pattern contrast.\n- `--step`: optional value for subpixel-interpolation around matches.\n- `--lr-maxdiff`: use a maximum left-right disparity difference as a postfilter instead of no-duplicates.\n\nOther settings are available; Try `bicos-cli -h` for details.\n\n## Benchmarking:\n\n```console\n$ meson test --benchmark -C builddir --interactive\n```\n\n## Light projection:\nFor starters, you may find https://github.com/Sir-Photch/VRRTest useful for projecting a light pattern using an aftermarket projector.\n\n## License\n\nThis library is licensed under the GNU Lesser General Public License v3.0 (or later).\nPlease see [COPYING](/COPYING) and [COPYING.LESSER](/COPYING.LESSER) for details.\n\n![LGPL-3.0-Logo](https://www.gnu.org/graphics/lgplv3-147x51.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjmuwrobotics%2Flibbicos","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjmuwrobotics%2Flibbicos","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjmuwrobotics%2Flibbicos/lists"}