{
  "id": 180921,
  "title": " The world of RANSAC",
  "url": "/competitions/landmark-recognition-2020/discussion/180921",
  "author_name": "",
  "post_date": "2020-09-06T22:23:47.911585400Z",
  "votes": 16,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Since Ransac is used in this competition, it might be worth reading more on the subject, and there is a lot to learn, and many recently published research reports about RANSAC and its corresponding algorithms.</p>\n<p>\"Image Matching Across Wide Baselines: From Paper to Practice\"<br>\n<a href=\"https://arxiv.org/pdf/2003.01587.pdf\" target=\"_blank\">https://arxiv.org/pdf/2003.01587.pdf</a></p>\n<p>\"Performance Evaluation of RANSAC Family\"<br>\n<a href=\"https://www.researchgate.net/publication/221259400_Performance_evaluation_of_RANSAC_family\" target=\"_blank\">https://www.researchgate.net/publication/221259400_Performance_evaluation_of_RANSAC_family</a></p>\n<p>\"MAGSAC: Marginalizing Sample Consensus\"<br>\n<a href=\"https://arxiv.org/pdf/1803.07469.pdf\" target=\"_blank\">https://arxiv.org/pdf/1803.07469.pdf</a></p>\n<p>\"Python wrapper of RANSAC for homography and fundamental matrix estimation from sparse correspondences. It implements LO-RANSAC and DEGENSAC.\"<br>\n<a href=\"https://github.com/ducha-aiki/pydegensac\" target=\"_blank\">https://github.com/ducha-aiki/pydegensac</a></p>\n<p>\"The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold\"<br>\n<a href=\"https://github.com/danini/magsac\" target=\"_blank\">https://github.com/danini/magsac</a><br>\n<a href=\"https://github.com/ducha-aiki/pymagsac\" target=\"_blank\">https://github.com/ducha-aiki/pymagsac</a></p>\n<p>Here is one notebook for testing<br>\n<a href=\"https://www.kaggle.com/camaskew/ransac-pydegensac-vs-scikit\" target=\"_blank\">https://www.kaggle.com/camaskew/ransac-pydegensac-vs-scikit</a></p>",
  "messages": [
    {
      "id": "1000903",
      "postDate": "09/06/2020 22:23:47",
      "content": "<p>Since Ransac is used in this competition, it might be worth reading more on the subject, and there is a lot to learn, and many recently published research reports about RANSAC and its corresponding algorithms.</p>\n<p>\"Image Matching Across Wide Baselines: From Paper to Practice\"<br>\n<a href=\"https://arxiv.org/pdf/2003.01587.pdf\" target=\"_blank\">https://arxiv.org/pdf/2003.01587.pdf</a></p>\n<p>\"Performance Evaluation of RANSAC Family\"<br>\n<a href=\"https://www.researchgate.net/publication/221259400_Performance_evaluation_of_RANSAC_family\" target=\"_blank\">https://www.researchgate.net/publication/221259400_Performance_evaluation_of_RANSAC_family</a></p>\n<p>\"MAGSAC: Marginalizing Sample Consensus\"<br>\n<a href=\"https://arxiv.org/pdf/1803.07469.pdf\" target=\"_blank\">https://arxiv.org/pdf/1803.07469.pdf</a></p>\n<p>\"Python wrapper of RANSAC for homography and fundamental matrix estimation from sparse correspondences. It implements LO-RANSAC and DEGENSAC.\"<br>\n<a href=\"https://github.com/ducha-aiki/pydegensac\" target=\"_blank\">https://github.com/ducha-aiki/pydegensac</a></p>\n<p>\"The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold\"<br>\n<a href=\"https://github.com/danini/magsac\" target=\"_blank\">https://github.com/danini/magsac</a><br>\n<a href=\"https://github.com/ducha-aiki/pymagsac\" target=\"_blank\">https://github.com/ducha-aiki/pymagsac</a></p>\n<p>Here is one notebook for testing<br>\n<a href=\"https://www.kaggle.com/camaskew/ransac-pydegensac-vs-scikit\" target=\"_blank\">https://www.kaggle.com/camaskew/ransac-pydegensac-vs-scikit</a></p>",
      "rawMarkdown": "Since Ransac is used in this competition, it might be worth reading more on the subject, and there is a lot to learn, and many recently published research reports about RANSAC and its corresponding algorithms.\n\n\"Image Matching Across Wide Baselines: From Paper to Practice\"\nhttps://arxiv.org/pdf/2003.01587.pdf\n\n\"Performance Evaluation of RANSAC Family\"\nhttps://www.researchgate.net/publication/221259400_Performance_evaluation_of_RANSAC_family\n\n\"MAGSAC: Marginalizing Sample Consensus\"\nhttps://arxiv.org/pdf/1803.07469.pdf\n\n\"Python wrapper of RANSAC for homography and fundamental matrix estimation from sparse correspondences. It implements LO-RANSAC and DEGENSAC.\"\nhttps://github.com/ducha-aiki/pydegensac\n\n\"The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold\"\nhttps://github.com/danini/magsac\nhttps://github.com/ducha-aiki/pymagsac\n\nHere is one notebook for testing\nhttps://www.kaggle.com/camaskew/ransac-pydegensac-vs-scikit",
      "votes": null
    },
    {
      "id": "1032591",
      "postDate": "09/30/2020 10:01:18",
      "content": "<p>And CVPR 2020 tutorial on RANSAC, videos are here <a href=\"http://cmp.felk.cvut.cz/cvpr2020-ransac-tutorial/\" target=\"_blank\">http://cmp.felk.cvut.cz/cvpr2020-ransac-tutorial/</a></p>",
      "rawMarkdown": "And CVPR 2020 tutorial on RANSAC, videos are here http://cmp.felk.cvut.cz/cvpr2020-ransac-tutorial/",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1032591,
      "author_name": "oldufo",
      "author_url": "",
      "post_date": "09/30/2020 10:01:18",
      "content": "<p>And CVPR 2020 tutorial on RANSAC, videos are here <a href=\"http://cmp.felk.cvut.cz/cvpr2020-ransac-tutorial/\" target=\"_blank\">http://cmp.felk.cvut.cz/cvpr2020-ransac-tutorial/</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1000903": "Since Ransac is used in this competition, it might be worth reading more on the subject, and there is a lot to learn, and many recently published research reports about RANSAC and its corresponding algorithms.\n\n\"Image Matching Across Wide Baselines: From Paper to Practice\"\nhttps://arxiv.org/pdf/2003.01587.pdf\n\n\"Performance Evaluation of RANSAC Family\"\nhttps://www.researchgate.net/publication/221259400_Performance_evaluation_of_RANSAC_family\n\n\"MAGSAC: Marginalizing Sample Consensus\"\nhttps://arxiv.org/pdf/1803.07469.pdf\n\n\"Python wrapper of RANSAC for homography and fundamental matrix estimation from sparse correspondences. It implements LO-RANSAC and DEGENSAC.\"\nhttps://github.com/ducha-aiki/pydegensac\n\n\"The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold\"\nhttps://github.com/danini/magsac\nhttps://github.com/ducha-aiki/pymagsac\n\nHere is one notebook for testing\nhttps://www.kaggle.com/camaskew/ransac-pydegensac-vs-scikit",
    "1032591": "And CVPR 2020 tutorial on RANSAC, videos are here http://cmp.felk.cvut.cz/cvpr2020-ransac-tutorial/"
  },
  "source": "meta"
}