{
  "id": "2209.15056",
  "version": "v1",
  "published": "2022-09-29T18:57:52.000Z",
  "updated": "2022-09-29T18:57:52.000Z",
  "title": "Graph Attention Network for Camera Relocalization on Dynamic Scenes",
  "authors": [
    "Mohamed Amine Ouali",
    "Mohamed Bouguessa",
    "Riadh Ksantini"
  ],
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.LG"
  ],
  "abstract": "We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Previous approaches built a scene-dependent model that explicitly or implicitly embeds the structure of the scene. They use convolution neural networks or decision trees to establish 2D/3D-3D correspondences. Such a mapping overfits the target scene and does not generalize well to dynamic changes in the environment. Our work introduces a novel approach to solve the camera relocalization problem by using the available triangle mesh. Our 3D-3D matching framework consists of three blocks: (1) a graph neural network to compute the embedding of mesh vertices, (2) a convolution neural network to compute the embedding of grid cells defined on the RGB-D image, and (3) a neural network model to establish the correspondence between the two embeddings. These three components are trained end-to-end. To predict the final pose, we run the RANSAC algorithm to generate camera pose hypotheses, and we refine the prediction using the point-cloud representation. Our approach significantly improves the camera pose accuracy of the state-of-the-art method from $0.358$ to $0.506$ on the RIO10 benchmark for dynamic indoor camera relocalization.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-09-29T18:57:52.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "dynamic scenes",
      "convolution neural network",
      "generate camera pose hypotheses",
      "dynamic indoor camera relocalization",
      "scene triangle mesh representation"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}