AdaptVPR：基於路線感知的困難正樣本生成方法應用於穩健視覺場所辨識

摘要

視覺地點辨識（Visual Place Recognition, VPR）藉由檢索同一或鄰近地點的資料庫影像來定位查詢影像，然而其強健性常因光照、天氣、季節變化與動態遮蔽所造成的域偏移而下降。其中一個因素在於現有的訓練資料中，同一地點的外觀多樣性有限。為解決此問題，我們提出 AdaptVPR，一個路徑感知的生成式擴增框架，旨在為強健的 VPR 訓練構建同地困難正樣本。AdaptVPR 首先使用視覺語言模型解析場景屬性並估計編輯可行性，同時由基於規則的排程器根據可編輯性分數與風險約束決定生成路徑。生成過程分為三個互補路徑：全域外觀路徑引入天氣、光照與時段的全域場景變化；局部遮蔽路徑插入合理的動態遮蔽物；雙重路徑結合兩類擾動，以產生更具挑戰性的外觀偏移。每個生成的候選樣本皆以 VPR 導向的驗證機制進行評估，該機制基於幾何一致性與外觀多樣性，在確保足夠外觀變異的同時，降低結構漂移的風險。全域候選樣本僅生成一次，若驗證失敗即遭拒絕；局部遮蔽與雙重候選樣本則運用驗證回饋來進行有限的提示詞精煉與重新生成。採用此框架，我們建構了 AdaptCities，包含 160K 個經驗證的合成同地困難正樣本。跨多個 VPR 基線與視覺基礎模型骨幹的實驗結果顯示，在標準基準上具有一致的增益，且在具挑戰性的域偏移下表現顯著改善，R@1 增益最高可達 9.2%。原始碼與資料資源已公開於 https://github.com/chenshunpeng/AdaptVPR。

English

Visual Place Recognition (VPR) localizes a query image by retrieving database images of the same or nearby place, yet its robustness is often degraded by domain shifts arising from illumination, weather, seasonal changes, and dynamic occlusions. One contributing factor is the limited appearance diversity of the same place in existing training data. To address this issue, we propose AdaptVPR, a route-aware generative augmentation framework that constructs same-place hard positives for robust VPR training. AdaptVPR first uses a vision language model to parse scene attributes and estimate editing feasibility, while a rule-based scheduler determines the generation route according to editability scores and risk constraints. The generation process is decomposed into three complementary routes: the Global Appearance Route introduces global scene changes in weather, illumination, and time of day; the Local Occlusion Route inserts plausible dynamic occluders; and the Dual Route combines both types of perturbations to produce more challenging appearance shifts. Each generated candidate is evaluated using a VPR-oriented verification scheme based on geometric consistency and appearance diversity, reducing the risk of structural drift while ensuring sufficient appearance variation. Global candidates are generated once and rejected if verification fails, while Local Occlusion and Dual candidates use verification feedback for limited prompt refinement and regeneration. Using this framework, we construct AdaptCities, containing 160K verified synthetic same-place hard positives. Experiments across multiple VPR baselines and vision foundation backbones show consistent gains on standard benchmarks and substantial improvements under challenging domain shifts, with R@1 gains of up to 9.2%. The source code and data resources are publicly available at https://github.com/chenshunpeng/AdaptVPR.