{
  "id": "2307.15381",
  "version": "v1",
  "published": "2023-07-28T08:05:36.000Z",
  "updated": "2023-07-28T08:05:36.000Z",
  "title": "AffineGlue: Joint Matching and Robust Estimation",
  "authors": [
    "Daniel Barath",
    "Dmytro Mishkin",
    "Luca Cavalli",
    "Paul-Edouard Sarlin",
    "Petr Hruby",
    "Marc Pollefeys"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "We propose AffineGlue, a method for joint two-view feature matching and robust estimation that reduces the combinatorial complexity of the problem by employing single-point minimal solvers. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches. Moreover, we derive a new minimal solver for homography estimation, requiring only a single affine correspondence (AC) and a gravity prior. Furthermore, we train a neural network to reject ACs that are unlikely to lead to a good model. AffineGlue is superior to the SOTA on real-world datasets, even when assuming that the gravity direction points downwards. On PhotoTourism, the AUC@10{\\deg} score is improved by 6.6 points compared to the SOTA. On ScanNet, AffineGlue makes SuperPoint and SuperGlue achieve similar accuracy as the detector-free LoFTR.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-07-28T08:05:36.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "robust estimation",
      "joint matching",
      "superglue achieve similar accuracy",
      "affineglue selects potential matches",
      "joint two-view feature"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}