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.
@article{arxiv.2601.06831,
title = {SARA: Scene-Aware Reconstruction Accelerator},
author = {Jee Won Lee and Hansol Lim and Minhyeok Im and Dohyeon Lee and Jongseong Brad Choi},
journal= {arXiv preprint arXiv:2601.06831},
year = {2026}
}
Comments
This work has been submitted to the 2026 International Conference on Pattern Recognition (ICPR) for possible publication