Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.01019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918111781847040 |
|---|---|
| author | Zeeshan, Muhammad Zaki, Umer Pasha, Syed Ahmed Khizar, Zaar |
| author_facet | Zeeshan, Muhammad Zaki, Umer Pasha, Syed Ahmed Khizar, Zaar |
| contents | Accurate 3D reconstruction from unstructured image collections is a key requirement in applications such as robotics, mapping, and scene understanding. While global Structure from Motion (SfM) techniques rely on full image connectivity and can be sensitive to noise or missing data, incremental SfM offers a more flexible alternative. By progressively incorporating new views into the reconstruction, it enables the system to recover scene structure and camera motion even in sparse or partially overlapping datasets. In this paper, we present a detailed implementation of the incremental SfM pipeline, focusing on the consistency of geometric estimation and the effect of iterative refinement through bundle adjustment. We demonstrate the approach using a real dataset and assess reconstruction quality through reprojection error and camera trajectory coherence. The results support the practical utility of incremental SfM as a reliable method for sparse 3D reconstruction in visually structured environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01019 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D Reconstruction via Incremental Structure From Motion Zeeshan, Muhammad Zaki, Umer Pasha, Syed Ahmed Khizar, Zaar Computer Vision and Pattern Recognition Optimization and Control Accurate 3D reconstruction from unstructured image collections is a key requirement in applications such as robotics, mapping, and scene understanding. While global Structure from Motion (SfM) techniques rely on full image connectivity and can be sensitive to noise or missing data, incremental SfM offers a more flexible alternative. By progressively incorporating new views into the reconstruction, it enables the system to recover scene structure and camera motion even in sparse or partially overlapping datasets. In this paper, we present a detailed implementation of the incremental SfM pipeline, focusing on the consistency of geometric estimation and the effect of iterative refinement through bundle adjustment. We demonstrate the approach using a real dataset and assess reconstruction quality through reprojection error and camera trajectory coherence. The results support the practical utility of incremental SfM as a reliable method for sparse 3D reconstruction in visually structured environments. |
| title | 3D Reconstruction via Incremental Structure From Motion |
| topic | Computer Vision and Pattern Recognition Optimization and Control |
| url | https://arxiv.org/abs/2508.01019 |