{
  "id": 170363,
  "title": "Maybe relevant",
  "url": "/competitions/landmark-retrieval-2020/discussion/170363",
  "author_name": "CPMP",
  "post_date": "2020-07-27T12:10:33.631000",
  "votes": 22,
  "comment_count": 2,
  "views": 0,
  "content": "<p>(sorry if already shared, I have not entered this comp hence do not read its forum).</p>\n\n<p>hloc - the hierarchical localization toolbox</p>\n\n<p>This is hloc, a modular toolbox for state-of-the-art 6-DoF visual localization. It implements Hierarchical Localization, leveraging image retrieval and feature matching, and is fast, accurate, and scalable. This codebase won the indoor/outdoor localization challenge at CVPR 2020, in combination with SuperGlue, our graph neural network for feature matching.</p>\n\n<p>With hloc, you can:</p>\n\n<pre><code>Reproduce our CVPR 2020 winning results on outdoor (Aachen) and indoor (InLoc) datasets\nRun Structure-from-Motion with SuperPoint+SuperGlue to localize with your own datasets\nEvaluate your own local features or image retrieval for visual localization\nImplement new localization pipelines and debug them easily 🔥\n</code></pre>\n\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F75976%2F0e4571478b992768c71ccdd0d5cc18b7%2Flocalisation.png?generation=1595851885503633&amp;alt=media\" alt=\"\"></p>\n\n<p><a href=\"https://github.com/cvg/Hierarchical-Localization\">https://github.com/cvg/Hierarchical-Localization</a></p>",
  "messages": [
    {
      "id": 947657,
      "postDate": "2020-07-27T12:10:33.630Z",
      "content": "<p>(sorry if already shared, I have not entered this comp hence do not read its forum).</p>\n\n<p>hloc - the hierarchical localization toolbox</p>\n\n<p>This is hloc, a modular toolbox for state-of-the-art 6-DoF visual localization. It implements Hierarchical Localization, leveraging image retrieval and feature matching, and is fast, accurate, and scalable. This codebase won the indoor/outdoor localization challenge at CVPR 2020, in combination with SuperGlue, our graph neural network for feature matching.</p>\n\n<p>With hloc, you can:</p>\n\n<pre><code>Reproduce our CVPR 2020 winning results on outdoor (Aachen) and indoor (InLoc) datasets\nRun Structure-from-Motion with SuperPoint+SuperGlue to localize with your own datasets\nEvaluate your own local features or image retrieval for visual localization\nImplement new localization pipelines and debug them easily 🔥\n</code></pre>\n\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F75976%2F0e4571478b992768c71ccdd0d5cc18b7%2Flocalisation.png?generation=1595851885503633&amp;alt=media\" alt=\"\"></p>\n\n<p><a href=\"https://github.com/cvg/Hierarchical-Localization\">https://github.com/cvg/Hierarchical-Localization</a></p>",
      "rawMarkdown": "(sorry if already shared, I have not entered this comp hence do not read its forum).\n\nhloc - the hierarchical localization toolbox\n\nThis is hloc, a modular toolbox for state-of-the-art 6-DoF visual localization. It implements Hierarchical Localization, leveraging image retrieval and feature matching, and is fast, accurate, and scalable. This codebase won the indoor/outdoor localization challenge at CVPR 2020, in combination with SuperGlue, our graph neural network for feature matching.\n\nWith hloc, you can:\n\n    Reproduce our CVPR 2020 winning results on outdoor (Aachen) and indoor (InLoc) datasets\n    Run Structure-from-Motion with SuperPoint+SuperGlue to localize with your own datasets\n    Evaluate your own local features or image retrieval for visual localization\n    Implement new localization pipelines and debug them easily 🔥\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F75976%2F0e4571478b992768c71ccdd0d5cc18b7%2Flocalisation.png?generation=1595851885503633&amp;alt=media)\n\nhttps://github.com/cvg/Hierarchical-Localization",
      "votes": 22
    },
    {
      "id": 947661,
      "postDate": "2020-07-27T12:12:28.900Z",
      "rawMarkdown": "",
      "isDeleted": true
    },
    {
      "id": 952520,
      "postDate": "2020-07-31T02:25:32.867Z",
      "content": "<p>Thanks. this will help! </p>",
      "rawMarkdown": "Thanks. this will help! "
    }
  ],
  "comments": [
    {
      "id": 947661,
      "author_name": "",
      "author_url": "",
      "post_date": "2020-07-27T12:12:28.900000",
      "content": "",
      "votes": 0,
      "replies": []
    },
    {
      "id": 952520,
      "author_name": "Mohit Duklan",
      "author_url": "",
      "post_date": "2020-07-31T02:25:32.867000",
      "content": "<p>Thanks. this will help! </p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "947657": "(sorry if already shared, I have not entered this comp hence do not read its forum).\n\nhloc - the hierarchical localization toolbox\n\nThis is hloc, a modular toolbox for state-of-the-art 6-DoF visual localization. It implements Hierarchical Localization, leveraging image retrieval and feature matching, and is fast, accurate, and scalable. This codebase won the indoor/outdoor localization challenge at CVPR 2020, in combination with SuperGlue, our graph neural network for feature matching.\n\nWith hloc, you can:\n\n    Reproduce our CVPR 2020 winning results on outdoor (Aachen) and indoor (InLoc) datasets\n    Run Structure-from-Motion with SuperPoint+SuperGlue to localize with your own datasets\n    Evaluate your own local features or image retrieval for visual localization\n    Implement new localization pipelines and debug them easily 🔥\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F75976%2F0e4571478b992768c71ccdd0d5cc18b7%2Flocalisation.png?generation=1595851885503633&amp;alt=media)\n\nhttps://github.com/cvg/Hierarchical-Localization",
    "947661": "",
    "952520": "Thanks. this will help! "
  }
}