HypeVPR:探索双曲空间用于透视到等距柱状投影的视觉位置识别
HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition
把描述子嵌入到双曲空间以显式编码「全景包含多个透视视角」的层次结构,并用层次化聚合在推理时无需重训练即可调节精度-效率折中,这一思路可迁移到任何需要跨视角/跨尺度匹配的检索式定位任务。
原文依据 HypeVPR leverages the intrinsic ability of hyperbolic space to represent hierarchical structures
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环境本身具有层次性,因为一幅全景视图天然地在其视场中包含并组织多个透视视图。捕捉这种层次结构对于有效的透视到等距柱状投影(P2E)视觉位置识别至关重要。在本工作中,我们提出 HypeVPR,一个位于双曲空间中的层次化嵌入框架,专门用于应对 P2E 匹配的挑战。HypeVPR 利用双曲空间表示层次结构的内在能力,使全景描述子既能编码宽泛的上下文信息,又能编码细粒度的局部细节。为此,我们提出一种层次化特征聚合机制,在双曲空间内组织从局部到全局的特征表示。此外,HypeVPR 的层次化组织天然支持在无需额外训练的情况下对精度-效率折中进行灵活控制,同时在不同图像类型之间保持稳健匹配。这一方式使 HypeVPR 在取得有竞争力性能的同时,显著加速检索并降低数据库存储需求。项目主页:https://suhan-woo.github.io/HypeVPR/
英文原文摘要 1191 字符
Visual environments are inherently hierarchical, as a panoramic view naturally encompasses and organizes multiple perspective views within its field. Capturing this hierarchy is crucial for effective perspective-to-equirectangular (P2E) visual place recognition. In this work, we introduce HypeVPR, a hierarchical embedding framework in hyperbolic space specifically designed to address the challenges of P2E matching. HypeVPR leverages the intrinsic ability of hyperbolic space to represent hierarchical structures, allowing panoramic descriptors to encode both broad contextual information and fine-grained local details. To this end, we propose a hierarchical feature aggregation mechanism that organizes local-to-global feature representations within hyperbolic space. Furthermore, HypeVPR's hierarchical organization naturally enables flexible control over the accuracy-efficiency trade-off without additional training, while maintaining robust matching across different image types. This approach enables HypeVPR to achieve competitive performance while significantly accelerating retrieval and reducing database storage requirements. Project page: https://suhan-woo.github.io/HypeVPR/