TopicGeo: An Efficient Unified Framework for Geolocation
Xin Wang, Xinlin Wang, Shuiping Gou
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3a77e0be-14b6-4222-b366-798a956fe072Builds on17
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- Geometric Transformer for Fast and Robust Point Cloud RegistrationZheng Qin, Hao Yu, Changjian Wang, Yulan Guo et al.CVPR 2022 · 436 citations
- COTR: Correspondence Transformer for Matching Across ImagesWei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi et al.ICCV 2021 · 318 citations
- Pixel-Perfect Structure-from-Motion with Featuremetric RefinementPhilipp Lindenberger, Paul-Edouard Sarlin, Viktor Larsson, Marc PollefeysICCV 2021 · 266 citations
Related papers
- 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 · 7 citations
- Adaptive Spot-Guided Transformer for Consistent Local Feature MatchingJiahuan Yu, Jiahao Chang, Jianfeng He, Tianzhu Zhang et al.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 et al.CVPR 2025
