多视角引导的相对位姿回归，实现快速高精度视觉重定位
MultiLoc: Multi-view Guided Relative Pose Regression for Fast and Robust Visual Re-Localization
- 融合多个参考视角与相机位姿，单次前向传播完成位姿估计
- 在WaySpots、Cambridge Landmarks等数据集上超越现有最优方法
- 适合需要实时、跨场景定位的应用，如机器人导航
相对位姿回归（RPR）在未见环境中泛化能力强，但受限于成对和局部空间视图。为此，我们提出MultiLoc，一种大规模训练的多视角引导式RPR模型，赋予相对位姿回归全局一致的空间与几何理解能力。该方法在一次前向传播中联合融合多个参考视图及其对应相机位姿，实现零样本、实时的精准位姿估计。为提供有效上下文，进一步提出基于共可见性的检索策略，选取几何相关参考视图。MultiLoc在视觉重定位任务上建立新基准，在WaySpots、Cambridge Landmarks和Indoor6等多个数据集上持续优于现有SOTA RPR方法。其位姿回归器在MegaDepth-1500、ScanNet-1500和ACID基准上表现优异，超越RPR、特征匹配及非回归方法，验证了其在室内、室外和自然环境中的强域泛化能力。代码将公开。
原文摘要 · Abstract (English)
Relative Pose Regression (RPR) generalizes well to unseen environments, but its performance is often limited due to pairwise and local spatial views. To this end, we propose MultiLoc, a novel multi-view guided RPR model trained at scale, equipping relative pose regression with globally consistent spatial and geometric understanding. Specifically, our method jointly fuses multiple reference views and their associated camera poses in a single forward pass, enabling accurate zero-shot pose estimation with real-time efficiency. To reliably supply informative context, we further propose a co-visibility-driven retrieval strategy for geometrically relevant reference view selection. MultiLoc establishes a new benchmark in visual re-localization, consistently outperforming existing state-of-the-art (SOTA) relative pose regression (RPR) methods across diverse datasets, including WaySpots, Cambridge Landmarks, and Indoor6. Furthermore, MultiLoc's pose regressor exhibits SOTA performance in relative pose estimation, surpassing RPR, feature matching and non-regression-based techniques on the MegaDepth-1500, ScanNet-1500, and ACID benchmarks. These results demonstrate robust domain generalization of MultiLoc across indoor, outdoor and natural environments. Code will be made publicly available.
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。