← 研踪 PaperTrailarXiv:2608.06847 · v2
What Should Visual Place Recognition Be Invariant To? Rethinking Condition Invariance in Visual Place Recognition
首次提交 2026-08-07 14:15
版本更新 2026-11-18 16:18
雷达观测 2026-11-19 19:07
摘要
Condition invariance in Visual Place Recognition (VPR) is typically evaluated by matching queries from one condition against a database from another condition. This tests the ability to recognize the same place when the query's condition differs from the database's condition. However, to map large environments, a database can be built from images collected by multiple robots or across multiple traversals under different conditions. In this setting, condition blindness---the ability to remain invariant to condition differences among database images---becomes important, but standard cross-condition evaluation does not provide a controlled assessment of this ability. Therefore, we introduce Distractor-Augmented Recall (DAR) to measure condition blindness in a controlled manner. Across eleven methods and six datasets, we find that differences in condition blindness can be larger than Recall@1 alone would suggest. To improve the condition blindness that DAR reveals, we compare three methods that make VPR descriptors more invariant to condition changes through post-processing. Among the three methods, we demonstrate INLP on a database built from multiple traversals under different conditions, showing that it can improve the performance of existing VPR methods.
作者备注:13 pages, 16 figures, 7 tables, including 4 pages of supplementary material
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-18 16:18 · 最新观测版本
What Should Visual Place Recognition Be Invariant To? Rethinking Condition Invariance in Visual Place Recognition
Condition invariance in Visual Place Recognition (VPR) is typically evaluated by matching queries from one condition against a database from another condition. This tests the ability to recognize the same place when the query's condition differs from the database's condition. However, to map large environments, a database can be built from images collected by multiple robots or across multiple traversals under different conditions. In this setting, condition blindness---the ability to remain invariant to condition differences among database images---becomes important, but standard cross-condition evaluation does not provide a controlled assessment of this ability. Therefore, we introduce Distractor-Augmented Recall (DAR) to measure condition blindness in a controlled manner. Across eleven methods and six datasets, we find that differences in condition blindness can be larger than Recall@1 alone would suggest. To improve the condition blindness that DAR reveals, we compare three methods that make VPR descriptors more invariant to condition changes through post-processing. Among the three methods, we demonstrate INLP on a database built from multiple traversals under different conditions, showing that it can improve the performance of existing VPR methods.
查看此版本解读 →查看此版本原文 ↗