{
  "id": "2208.14433",
  "version": "v1",
  "published": "2022-08-30T17:53:17.000Z",
  "updated": "2022-08-30T17:53:17.000Z",
  "title": "A Portable Multiscopic Camera for Novel View and Time Synthesis in Dynamic Scenes",
  "authors": [
    "Tianjia Zhang",
    "Yuen-Fui Lau",
    "Qifeng Chen"
  ],
  "comment": "To be presented at IROS2022",
  "categories": [
    "cs.CV",
    "cs.GR"
  ],
  "abstract": "We present a portable multiscopic camera system with a dedicated model for novel view and time synthesis in dynamic scenes. Our goal is to render high-quality images for a dynamic scene from any viewpoint at any time using our portable multiscopic camera. To achieve such novel view and time synthesis, we develop a physical multiscopic camera equipped with five cameras to train a neural radiance field (NeRF) in both time and spatial domains for dynamic scenes. Our model maps a 6D coordinate (3D spatial position, 1D temporal coordinate, and 2D viewing direction) to view-dependent and time-varying emitted radiance and volume density. Volume rendering is applied to render a photo-realistic image at a specified camera pose and time. To improve the robustness of our physical camera, we propose a camera parameter optimization module and a temporal frame interpolation module to promote information propagation across time. We conduct experiments on both real-world and synthetic datasets to evaluate our system, and the results show that our approach outperforms alternative solutions qualitatively and quantitatively. Our code and dataset are available at https://yuenfuilau.github.io.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-08-30T17:53:17.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "dynamic scene",
      "novel view",
      "time synthesis",
      "outperforms alternative solutions",
      "temporal frame interpolation module"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}