{
  "annotation_id": "e4d0e221-ecc3-434e-9d88-650dd77c572a",
  "date_created": "2026-02-17T05:53:08.803000Z",
  "date_modified": "2026-02-17T05:53:08.803000Z",
  "file_hash": "e227be888807748e0dc321243f4c002c10c0aeef32d257e3dfcc2b202ea8d78c",
  "private": false,
  "record": {
    "abstract": "We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs based on visual similarity alone, SARA introduces geometry-first pair selection by scoring reconstruction informativeness - the product of overlap and parallax - before expensive matching. A lightweight pre-matching stage uses mutual nearest neighbors and RANSAC to estimate these cues, then constructs an Information-Weighted Spanning Tree (IWST) augmented with targeted edges for loop closure, long-baseline anchors, and weak-view reinforcement. Compared to exhaustive matching, SARA reduces rotation errors by 46.5+-5.5% and translation errors by 12.5+-6.5% across modern learned detectors, while achieving at most 50x speedup through 98% pair reduction (from 30,848 to 580 pairs). This reduces matching complexity from quadratic to quasi-linear, maintaining within +-3% of baseline reconstruction metrics for 3D Gaussian Splatting and SVRaster.",
    "arxiv_id": "2601.06831",
    "authors": [
      "Jee Won Lee",
      "Hansol Lim",
      "Minhyeok Im",
      "Dohyeon Lee",
      "Jongseong Brad Choi"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "SARA: Scene-Aware Reconstruction Accelerator",
    "url": "https://arxiv.org/abs/2601.06831",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "68956e95-3908-4af6-a7ac-cd8776fcf7af",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}