{"slug": "colmap", "name": "COLMAP", "category": "media", "category_name": "Media and creative", "description": "", "recommenders": 4, "commenters": 6, "warners": 0, "score": 4.114, "rising": -1.31, "first": "2025-12-06", "latest": "2026-08-24", "why": "Personally, I recommend COLMAP + CloudCompare + MeshLab", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 3, "compare": 0, "warn": 0}, "spark": [0, 1, 1, 0, 0, 0, 0, 3, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Personally, I recommend COLMAP + CloudCompare + MeshLab", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/colmap/colmap", "official_url": "https://colmap.github.io", "pricing": "", "aliases": ["COLMAP"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 775871136, "item_id": 48491946, "url": "https://news.ycombinator.com/item?id=48491946", "by": "KaiserPro", "date": "2026-06-11", "stance": "recommend", "quote": "You can experiment at home using", "excerpt": "VPSs are much more effective at navigation at ground level in cities compared to GPS because of multi-path interference. However that data has a half life and needs to be refreshed. For flying drones, ground level data is really not that useful. mainly because you can't see it, because its obscured by trees, building and clouds. But, this is not a new thing. Google, Apple, facebook and niantic all have VPSs as do a b", "context": "", "use_case": "Structure-from-motion mapping", "switched_from": "", "story": "Pok\u00e9mon Go Scans Trained the Navigation Tech for Military Drones"}, {"id": 775577840, "item_id": 48473615, "url": "https://news.ycombinator.com/item?id=48473615", "by": "Joel_Mckay", "date": "2026-06-10", "stance": "recommend", "quote": "Personally, I recommend COLMAP + CloudCompare + MeshLab", "excerpt": "These should help narrow down the search, but ibfs commercial restrictions are now 404... and the original IP warnings seem missing/expired. https://github.com/openMVG/openMVG/blob/develop/COPYRIGHT.md https://github.com/cdcseacave/openMVS/blob/master/COPYRIGHT.md Personally, I recommend COLMAP + CloudCompare + MeshLab, but the Mozilla Public License 2.0 should address IP license issues if the author is also the righ", "context": "", "use_case": "photogrammetry", "switched_from": "", "story": "OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision"}, {"id": 774428467, "item_id": 48401779, "url": "https://news.ycombinator.com/item?id=48401779", "by": "Yen", "date": "2026-06-04", "stance": "recommend", "quote": "Then the images are handed to COLMAP (https://github.com/colmap/colmap), using the 'global mapper' option.", "excerpt": "I recently got into splatting. I looked for some good all-in-one tutorials, but didn't find any, and mostly muddled through through trial and error and LLM assistance. I present this workflow as a straight-line pipeline, though in practice it took a lot of iteration and backtracking and rework to get the final result. Here's what worked for me: I captured a video on a smartphone camera, using the OpenCamera app. Spec", "context": "", "use_case": "camera pose registration", "switched_from": "", "story": "Gaussian Point Splatting"}, {"id": 744965792, "item_id": 46560362, "url": "https://news.ycombinator.com/item?id=46560362", "by": "riotnrrd", "date": "2026-01-09", "stance": "recommend", "quote": "COLMAP is the tool most people use for the latter.", "excerpt": "That's a pretty well-solved problem at this point, if you want to do it yourself. You'll want some kind of NeRF tool and a way to calculate the camera poses of the photos you took. COLMAP is the tool most people use for the latter. I'd recommend trying Instant Neural Graphics Primitives (https://github.com/NVlabs/instant-ngp) from NVIDIA. It's a couple years old, so not state-of-the-art, but it runs on just about any", "context": "", "use_case": "Camera pose estimation", "switched_from": "", "story": "Revelium Studio turns a single image into a navigable 3D Gaussian Splat model"}, {"id": 738809489, "item_id": 46175593, "url": "https://news.ycombinator.com/item?id=46175593", "by": "KaiserPro", "date": "2025-12-06", "stance": "recommend", "quote": "less user friendly version of colmap", "excerpt": "A number of startups did this in 2017-2020 (Scape, Mapillary, Niantic, google, apple and a a few others who's names I've forgotten) With consumer cameras and GPS you can make pretty good maps, vaguely automatically. Keeping them up to date was mostly down to making sure that you had enough overlap in the data at different times. The big thing for that generation of companies was AR, and making AR games accurate. This", "context": "", "use_case": "", "switched_from": "", "story": "Mapping Amazing: Bee Maps"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["3d reconstruction from street imagery", "structure-from-motion mapping", "photogrammetry", "camera pose registration", "3d reconstruction / structure from motion", "camera pose estimation"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47398479", "title": "'Pok\u00e9mon Go' players unknowingly trained delivery robots with 30B images", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49422784", "title": "The entire city of San Francisco as a video game", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48487029", "title": "Pok\u00e9mon Go Scans Trained the Navigation Tech for Military Drones", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48421858", "title": "OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48396792", "title": "Gaussian Point Splatting", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46557352", "title": "Revelium Studio turns a single image into a navigable 3D Gaussian Splat model", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {"neutral": 2}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 3}, "2026-07": {}, "2026-08": {"neutral": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 790798592, "item_id": 49424912, "url": "https://news.ycombinator.com/item?id=49424912", "by": "K0IN", "date": "2026-08-24", "stance": "neutral", "quote": "colmap to reconstruct 3d chunks", "excerpt": "funny timing, i was exploring the same, some friends and me play alot of geogussr (a game where you put into streetview somewhere on the world, and have to find out where) lately. I want to make it more video game like, cause the jumps of google maps make me motion sick. I used google streetview as image source (cause you need to read signs, cars, see geometry) and colmap to reconstruct 3d chunks. But it never really", "context": "", "use_case": "3D reconstruction from street imagery", "switched_from": "", "story": "The entire city of San Francisco as a video game"}, {"id": 775871136, "item_id": 48491946, "url": "https://news.ycombinator.com/item?id=48491946", "by": "KaiserPro", "date": "2026-06-11", "stance": "recommend", "quote": "You can experiment at home using", "excerpt": "VPSs are much more effective at navigation at ground level in cities compared to GPS because of multi-path interference. However that data has a half life and needs to be refreshed. For flying drones, ground level data is really not that useful. mainly because you can't see it, because its obscured by trees, building and clouds. But, this is not a new thing. Google, Apple, facebook and niantic all have VPSs as do a b", "context": "", "use_case": "Structure-from-motion mapping", "switched_from": "", "story": "Pok\u00e9mon Go Scans Trained the Navigation Tech for Military Drones"}, {"id": 775577840, "item_id": 48473615, "url": "https://news.ycombinator.com/item?id=48473615", "by": "Joel_Mckay", "date": "2026-06-10", "stance": "recommend", "quote": "Personally, I recommend COLMAP + CloudCompare + MeshLab", "excerpt": "These should help narrow down the search, but ibfs commercial restrictions are now 404... and the original IP warnings seem missing/expired. https://github.com/openMVG/openMVG/blob/develop/COPYRIGHT.md https://github.com/cdcseacave/openMVS/blob/master/COPYRIGHT.md Personally, I recommend COLMAP + CloudCompare + MeshLab, but the Mozilla Public License 2.0 should address IP license issues if the author is also the righ", "context": "", "use_case": "photogrammetry", "switched_from": "", "story": "OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision"}, {"id": 774428467, "item_id": 48401779, "url": "https://news.ycombinator.com/item?id=48401779", "by": "Yen", "date": "2026-06-04", "stance": "recommend", "quote": "Then the images are handed to COLMAP (https://github.com/colmap/colmap), using the 'global mapper' option.", "excerpt": "I recently got into splatting. I looked for some good all-in-one tutorials, but didn't find any, and mostly muddled through through trial and error and LLM assistance. I present this workflow as a straight-line pipeline, though in practice it took a lot of iteration and backtracking and rework to get the final result. Here's what worked for me: I captured a video on a smartphone camera, using the OpenCamera app. Spec", "context": "", "use_case": "camera pose registration", "switched_from": "", "story": "Gaussian Point Splatting"}, {"id": 758415360, "item_id": 47400960, "url": "https://news.ycombinator.com/item?id=47400960", "by": "5-", "date": "2026-03-16", "stance": "neutral", "quote": "", "excerpt": "see this 2007 talk: https://www.ted.com/talks/blaise_aguera_y_arcas_how_photosynth_can_connect_the_world_s_images i remember this being available in google maps in 2008 or so. fun technology!", "context": "", "use_case": "", "switched_from": "", "story": "'Pok\u00e9mon Go' players unknowingly trained delivery robots with 30B images"}, {"id": 758414352, "item_id": 47400897, "url": "https://news.ycombinator.com/item?id=47400897", "by": "KaiserPro", "date": "2026-03-16", "stance": "neutral", "quote": "fed that data into a more modern version of colmap", "excerpt": "Niantic are a number of people who are doing this. Its not that clear from the article, but niantic spatial are using the images captured from users to create a 3d model of \"THE WORLD\" or where people play pokemon go. They have then fed that data into a more modern version of colmap (https://github.com/colmap/colmap) to create a point cloud. Then the engineering to make sure that point cloud is aligned accurately and", "context": "", "use_case": "3D reconstruction / structure from motion", "switched_from": "", "story": "'Pok\u00e9mon Go' players unknowingly trained delivery robots with 30B images"}, {"id": 744965792, "item_id": 46560362, "url": "https://news.ycombinator.com/item?id=46560362", "by": "riotnrrd", "date": "2026-01-09", "stance": "recommend", "quote": "COLMAP is the tool most people use for the latter.", "excerpt": "That's a pretty well-solved problem at this point, if you want to do it yourself. You'll want some kind of NeRF tool and a way to calculate the camera poses of the photos you took. COLMAP is the tool most people use for the latter. I'd recommend trying Instant Neural Graphics Primitives (https://github.com/NVlabs/instant-ngp) from NVIDIA. It's a couple years old, so not state-of-the-art, but it runs on just about any", "context": "", "use_case": "Camera pose estimation", "switched_from": "", "story": "Revelium Studio turns a single image into a navigable 3D Gaussian Splat model"}, {"id": 738809489, "item_id": 46175593, "url": "https://news.ycombinator.com/item?id=46175593", "by": "KaiserPro", "date": "2025-12-06", "stance": "recommend", "quote": "less user friendly version of colmap", "excerpt": "A number of startups did this in 2017-2020 (Scape, Mapillary, Niantic, google, apple and a a few others who's names I've forgotten) With consumer cameras and GPS you can make pretty good maps, vaguely automatically. Keeping them up to date was mostly down to making sure that you had enough overlap in the data at different times. The big thing for that generation of companies was AR, and making AR games accurate. This", "context": "", "use_case": "", "switched_from": "", "story": "Mapping Amazing: Bee Maps"}]}