通过子图一致性剔除错误连接，提升全局SfM在模糊图像下的鲁棒性。
Robust Global Structure-from-Motion via View Graph Pruning
- 用局部一致子图生成可靠位姿，作为判断边可靠性的依据
- 基于RANSAC跨子图剔除不一致边，显著降低错误匹配影响
- 适合处理有视觉混淆的无序或序列图像，尤其利于新视角合成
结构从运动（SfM）旨在从无序图像中估计相机位姿并重建三维结构。与增量式SfM相比，全局SfM通过基于成对匹配构建的视图图联合估计相机位姿，具有更好的可扩展性。然而，其性能极易受视觉模糊匹配引起的错误边影响，可能导致相机注册错误和重建伪影。本文提出一种基于子图引导的视图图剪枝框架，以增强全局SfM的鲁棒性。核心思想是利用可靠子图的内部一致性识别并移除不可靠连接。具体而言，首先将视图图划分为局部一致子图，并在每个子图内执行全局SfM以获得可靠相机位姿；随后在子图间应用基于RANSAC的边剪枝以去除不一致边；最后在优化后的视图图上重新进行全局SfM。在存在视觉模糊、顺序及无序图像的数据集上的大量实验表明，该方法在挑战性条件下显著提升了全局SfM的鲁棒性。进一步的神经渲染评估显示，改进的相机估计带来了更高质量的新视角合成结果。
原文摘要 · Abstract (English)
Structure-from-Motion (SfM) aims to estimate camera poses and reconstruct 3D structures from a collection of unordered images. Compared with incremental SfM, global SfM achieves better scalability by jointly estimating camera poses based on a view graph constructed from pairwise correspondences. However, its performance is highly sensitive to erroneous edges caused by visually ambiguous matches, which may lead to incorrect camera registration and reconstruction artifacts. In this work, we propose a subgraph-guided view graph pruning framework for robust global SfM. Our key idea is to exploit the internal consistency of reliable subgraphs to identify and remove unreliable connections. Specifically, we first partition the view graph into locally consistent subgraphs and perform global SfM within each subgraph to obtain reliable camera poses. We then apply RANSAC-based edge pruning across subgraphs to remove inconsistent edges, and finally perform global SfM on the refined view graph. Extensive experiments on ambiguous, sequential, and unordered image datasets demonstrate that our method improves the robustness of global SfM under challenging conditions. Further evaluation with neural rendering shows that the improved camera estimation leads to higher-quality novel view synthesis results.
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。