TRAIL:面向无序数据库的轨迹感知视觉地点识别
TRAIL: Trajectory-Aware Visual Place Recognition against Unordered Databases
浏览论文内容
中文总结 AI 辅助
TRAIL提出一种基于条件随机场的轨迹感知视觉地点识别框架,利用查询序列上下文在无序数据库中定位图像,无需数据库序列结构,作为轻量级后处理层可将基线性能提升高达8.3个百分点。
中文摘要 AI 辅助
现代视觉地点识别(VPR)方法在标准基准上表现出色,但在特征贫乏的环境中仍然脆弱。通过孤立地处理每个查询图像,它们丢弃了任何真实轨迹中的序列上下文。我们形式化了一个利用这种上下文的任务:给定一个查询序列,在无序参考数据库中定位最终图像——与序列到序列方法不同,这不需要数据库具有序列结构。我们提出了TRAIL(轨迹感知图像定位),一个基于条件随机场(CRF)的原则性框架,结合了用于视觉相似性和相机运动一致性的学习函数,随着每个查询的到来细化候选参考的分布。作为任何预训练VPR骨干之上的轻量级后处理层,TRAIL在我们的主要基准上将最先进的基线提高了高达8.3个百分点,无需重新训练即可迁移到未见数据集,并在视觉线索稀缺的地方带来最大增益。
英文摘要
Modern Visual Place Recognition (VPR) methods excel on standard benchmarks yet remain brittle in feature-poor environments. By treating each query image in isolation, they discard the sequential context in any real trajectory. We formalize a task that exploits this context: given a query sequence, localize the final image against an unordered reference database -- which, unlike sequence-to-sequence methods, requires no sequential structure in the database. We propose TRAIL (TRajectory-Aware Image Localization), a principled framework based on Conditional Random Fields (CRF) that combines learned functions for visual similarity and for camera-motion consistency, refining a distribution over candidate references as each query arrives. A lightweight post-processing layer atop any pre-trained VPR backbone, TRAIL improves a state-of-the-art baseline by up to 8.3 percentage points on our primary benchmark, transfers to unseen datasets without retraining, and delivers its largest gains where visual cues are scarce.
发表机构
- Visual Geometry Group (VGG), University of Oxford(牛津大学视觉几何组(VGG))
- Helsing(赫尔辛公司)
机构由 AI 辅助整理,请以论文原文为准。