TopicGeo: An Efficient Unified Framework for Geolocation
Xin Wang, Xinlin Wang, Shuiping Gou
2025年份
2被引次数
摘要
Figure 1. The visual geolocation results of our TopicGeo, and typical retrieval and matching approaches: Earthloc [4], SelaVPR [29], and LoFTR [47]
. "Recall" represents retrieval results. The color-coded lines show matching correctness: red for higher-error matches, green for higher-precision ones. In various scenes, our method accurately retrieves the target base image containing the query image from the database, while establishing pixel-level correspondence between the smaller query and large-scale retrieved image.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper17
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn 等ICLR 2021 · 被引用 21,477 次
- Geometric Transformer for Fast and Robust Point Cloud RegistrationZheng Qin, Hao Yu, Changjian Wang, Yulan Guo 等CVPR 2022 · 被引用 436 次
- COTR: Correspondence Transformer for Matching Across ImagesWei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi 等ICCV 2021 · 被引用 318 次
- Pixel-Perfect Structure-from-Motion with Featuremetric RefinementPhilipp Lindenberger, Paul-Edouard Sarlin, Viktor Larsson, Marc PollefeysICCV 2021 · 被引用 266 次
相关 Paper
- VIGOR: Cross-View Image Geo-Localization Beyond One-to-One RetrievalSijie Zhu, Taojiannan Yang, Chen ChenCVPR 2021
- On the Estimation of Image-Matching Uncertainty in Visual Place RecognitionMubariz Zaffar, Liangliang Nan, Julian F. P. KooijCVPR 2024 · 被引用 7 次
- Adaptive Spot-Guided Transformer for Consistent Local Feature MatchingJiahuan Yu, Jiahao Chang, Jianfeng He, Tianzhu Zhang 等CVPR 2023
- Around the World in 80 Timesteps: A Generative Approach to Global Visual GeolocationNicolas Dufour, Vicky Kalogeiton, David Picard, Loïc LandrieuCVPR 2025
- RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-EmbeddingsAayush Dhakal, Srikumar Sastry, Subash Khanal, Adeel Ahmad 等CVPR 2025
