Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.06831 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918281508552704 |
|---|---|
| author | Lee, Jee Won Lim, Hansol Im, Minhyeok Lee, Dohyeon Choi, Jongseong Brad |
| author_facet | Lee, Jee Won Lim, Hansol Im, Minhyeok Lee, Dohyeon Choi, Jongseong Brad |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06831 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SARA: Scene-Aware Reconstruction Accelerator Lee, Jee Won Lim, Hansol Im, Minhyeok Lee, Dohyeon Choi, Jongseong Brad Computer Vision and Pattern Recognition 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. |
| title | SARA: Scene-Aware Reconstruction Accelerator |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.06831 |