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.

翻译：本文提出SARA（场景感知重建加速器），一种面向运动恢复结构（SfM）的几何驱动图像对选择模块。与传统仅基于视觉相似性选择图像对的流程不同，SARA引入几何优先的图像对选择策略，在耗时的匹配步骤之前通过计算重建信息量（即重叠度与视差的乘积）进行评分。该模块通过轻量级预匹配阶段，利用互最近邻与RANSAC算法估计几何线索，进而构建信息加权生成树（IWST），并通过添加定向边实现闭环检测、长基线锚点强化及弱视角增强。相较于穷举匹配，SARA在现代学习式检测器上使旋转误差降低46.5±5.5%，平移误差降低12.5±6.5%，同时通过98%的图像对削减（从30,848对降至580对）实现最高50倍的加速效果。该方法将匹配复杂度从二次方降至拟线性，在3D高斯溅射与SVRaster重建任务中保持基准重建指标±3%以内的波动。