{
  "annotation_id": "d2c608ab-4a96-4aad-82cf-60366ba9c2f3",
  "date_created": "2026-02-17T05:53:15.840000Z",
  "date_modified": "2026-02-17T05:53:15.840000Z",
  "file_hash": "6a63dec3ddd7a943fb49f4cee27ec4386573c5f43e1d053713791b5889f2973d",
  "private": false,
  "record": {
    "abstract": "We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric grounding on complex surfaces, sometimes producing results that contain inconsistencies. Geo-NVS-w addresses this limitation by leveraging an underlying geometric representation based on a Signed Distance Function (SDF) to guide the rendering process. This is complemented by a novel Geometry-Preservation Loss which ensures that fine structural details are preserved. Our framework achieves competitive rendering performance, while demonstrating a 4-5x reduction reduction in energy consumption compared to similar methods. We demonstrate that Geo-NVS-w is a robust method for in-the-wild NVS, yielding photorealistic results with sharp, geometrically coherent details.",
    "arxiv_id": "2601.08371",
    "authors": [
      "Anastasios Tsalakopoulos",
      "Angelos Kanlis",
      "Evangelos Chatzis",
      "Antonis Karakottas",
      "Dimitrios Zarpalas"
    ],
    "categories": [
      "cs.CV",
      "cs.AI",
      "cs.GR",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer",
    "url": "https://arxiv.org/abs/2601.08371",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "90acd265-7715-4d52-bc33-09f83d7eb3ee",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}