SARA通过几何信息优化图像配对，显著提速3D重建且精度不降。
SARA: Scene-Aware Reconstruction Accelerator
- 先算几何信息再选图对，用重叠与视差评分
- 配对数从3万减到580，速度提升50倍
- 适合大规模场景重建，尤其加速弱视图场景
我们提出SARA（场景感知重建加速器），一种面向运动恢复结构（SfM）的几何驱动配对选择模块。不同于仅依赖视觉相似性的传统流程，SARA采用几何优先的配对策略，通过重叠度与视差的乘积评估重建信息量，在昂贵的特征匹配前完成筛选。轻量级预匹配阶段利用互近邻和RANSAC估计这些线索，构建信息加权生成树（IWST），并加入环路闭合、长基线锚点和弱视图增强边。相比全量匹配，SARA在现代学习型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%，同时实现最多50倍加速，配对数减少98%（从30,848降至580）。匹配复杂度从二次方降至准线性，对3D高斯点云与SVRaster重建指标保持±3%以内，基本无损失。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。