超越一阶：用于不变视觉地点识别的黎曼几何学习
Beyond First-Order: Learning Riemannian Geometries for Invariant Visual Place Recognition
AI总结：
本文提出RIA框架，通过在对称正定流形上建模二阶场景结构，提升视觉地点识别在极端环境变化下的鲁棒性与准确性。
摘要：
视觉地点识别（VPR）需要对环境和视角剧烈变化具有鲁棒性的表示。现有聚合方法要么依赖于大量监督训练，要么依赖于一阶池化，往往难以在极端变化下保持结构相关性或导致高适应成本。在本文中，我们提出了黎曼不变聚合（RIA），一种统一的几何框架，明确建模对称正定（SPD）流形上的二阶场景结构。通过将扰动视为可处理的全等变换，RIA利用几何感知的黎曼映射将协方差描述符投影到线性化的欧几里得空间，有效保持不变的结构组件并抑制噪声。广泛评估表明，RIA在零样本性能上与监督方法相当，并通过简单的微调实现了最先进的准确性，特别是在非结构化环境中。源代码将被释放。
英文摘要：
Visual Place Recognition (VPR) demands representations robust to drastic environmental and viewpoint shifts. Existing aggregation paradigms either depend on extensive supervised training or rely on first-order pooling, often struggling to preserve structural correlations under extreme shifts or incurring high adaptation costs. In this work, we propose Riemannian Invariant Aggregation (RIA), a unified geometric framework that explicitly models second-order scene structure on the Symmetric Positive Definite (SPD) manifold. By treating perturbations as tractable congruence transformations, RIA leverages geometry-aware Riemannian mappings to project covariance descriptors into a linearized Euclidean space, effectively preserving invariant structural components while suppressing noise. Extensive evaluations demonstrate that RIA achieves zero-shot performance comparable to supervised methods, and establishes state-of-the-art accuracy with simple fine-tuning, particularly in unstructured environments. The source code will be released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
