基于特征高斯泼溅最近视角合成的分层视觉重定位
Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting
将 Feature Gaussian Splatting 作为场景表示用于分层重定位，并用自适应视角检索合成与查询视角更接近的虚拟候选图，缓解数据库图像稀疏问题；同时提出粗阶段用高斯渲染特征、精阶段用图像直接提取特征的混合匹配策略，可直接迁移到任何基于特征匹配的位姿估计流程。
原文依据 we propose an adaptive viewpoint retrieval method that synthesizes virtual candidates with viewpoints more closely aligned with the query
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉重定位是三维计算机视觉领域的一项基础任务，其目标是在相机重新访问已知场景时估计相机位姿。基于点的分层重定位方法已展现出较强的可扩展性与效率，但往往受限于稀疏的图像观测和较弱的特征匹配。本文提出 SplatHLoc，一种以特征高斯泼溅作为场景表示的新型分层视觉重定位框架。针对数据库图像稀疏的问题，我们提出一种自适应视角检索方法，通过合成视点与查询更接近的虚拟候选图像，提升初始位姿估计的精度。在特征匹配方面，我们观察到高斯渲染特征与直接从图像中提取的特征在两阶段匹配过程中各有所长：前者在粗阶段表现更优，而后者在精阶段更为有效。因此，我们引入一种混合特征匹配策略，从而实现更精确、更高效的位姿估计。在室内与室外数据集上的大量实验表明，SplatHLoc 提升了视觉重定位的鲁棒性，并取得了新的最优性能。
英文原文摘要 1278 字符
Visual relocalization is a fundamental task in the field of 3D computer vision, estimating a camera's pose when it revisits a previously known scene. While point-based hierarchical relocalization methods have shown strong scalability and efficiency, they are often limited by sparse image observations and weak feature matching. In this work, we propose SplatHLoc, a novel hierarchical visual relocalization framework that uses Feature Gaussian Splatting as the scene representation. To address the sparsity of database images, we propose an adaptive viewpoint retrieval method that synthesizes virtual candidates with viewpoints more closely aligned with the query, thereby improving the accuracy of initial pose estimation. For feature matching, we observe that Gaussian-rendered features and those extracted directly from images exhibit different strengths across the two-stage matching process: the former performs better in the coarse stage, while the latter proves more effective in the fine stage. Therefore, we introduce a hybrid feature matching strategy, enabling more accurate and efficient pose estimation. Extensive experiments on both indoor and outdoor datasets show that SplatHLoc enhances the robustness of visual relocalization, setting a new state-of-the-art.