{"ID":2882358,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10667","arxiv_id":"2508.10667","title":"AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models","abstract":"Large visual language models (LVLMs) have demonstrated impressive performance in coarse-grained geo-localization at the country or city level, but they struggle with fine-grained street-level localization within urban areas. In this paper, we explore integrating city-wide address localization capabilities into LVLMs, facilitating flexible address-related question answering using street-view images. A key challenge is that the street-view visual question-and-answer (VQA) data provides only microscopic visual cues, leading to subpar performance in fine-tuned models. To tackle this issue, we incorporate perspective-invariant satellite images as macro cues and propose cross-view alignment tuning including a satellite-view and street-view image grafting mechanism, along with an automatic label generation mechanism. Then LVLM's global understanding of street distribution is enhanced through cross-view matching. Our proposed model, named AddressVLM, consists of two-stage training protocols: cross-view alignment tuning and address localization tuning. Furthermore, we have constructed two street-view VQA datasets based on image address localization datasets from Pittsburgh and San Francisco. Qualitative and quantitative evaluations demonstrate that AddressVLM outperforms counterpart LVLMs by over 9% and 12% in average address localization accuracy on these two datasets, respectively.","short_abstract":"Large visual language models (LVLMs) have demonstrated impressive performance in coarse-grained geo-localization at the country or city level, but they struggle with fine-grained street-level localization within urban areas. In this paper, we explore integrating city-wide address localization capabilities into LVLMs, f...","url_abs":"https://arxiv.org/abs/2508.10667","url_pdf":"https://arxiv.org/pdf/2508.10667v1","authors":"[\"Shixiong Xu\",\"Chenghao Zhang\",\"Lubin Fan\",\"Yuan Zhou\",\"Bin Fan\",\"Shiming Xiang\",\"Gaofeng Meng\",\"Jieping Ye\"]","published":"2025-08-14T14:06:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}