NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization
Shitao Tang, Sicong Tang, Andrea Tagliasacchi, Ping Tan, Yasutaka Furukawa
Abstract
Figure 1. The paper presents neural coordinate mapping (NeuMap) for camera localization. NeuMap encodes a scene into a set of codes and uses a scene-agnostic transformer to decode the coordinates of key-points in a query image. The right compares the localization accuracy and the data size for Aachen Night benchmark. The accuracy is averaged over three translation/rotation error thresholds (0.25m, 2 • ), (0.5m, 5 • ), or (5m, 10 • ). NeuMap and Squeezer control representation sizes and are illustrated by curves with multiple data points.
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 5b3d51bf-ddc8-4f4f-b1ff-bb03489a43d4Cited by top-tier papers13
- ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-TrainingLeonard Bruns, Axel Barroso-Laguna, Tommaso Cavallari, Áron Monszpart et al.ICCV 2025 · 5 citations
- ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian SplattingYingdong Gu, Shaocheng Yan, Zhenjun Zhao, Yuan Kou et al.CVPR 2026 · 3 citations
- A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image FeaturesAxel Barroso-Laguna, Tommaso Cavallari, Victor Prisacariu, Eric BrachmannICLR 2026 · 3 citations
- Trafficloc: Localizing Traffic Surveillance Cameras in 3D ScenesYan Xia, Yunxiang Lu, Rui Song, Oussema Dhaouadi et al.ICCV 2025 · 2 citations
- 3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature FusionJunyi Wang, Yuze Wang, Wantong Duan, Meng Wang et al.NeurIPS 2025 · 1 citation
Builds on16
- Learning With Average Precision: Training Image Retrieval With a Listwise LossJérôme Revaud, Jon Almazán, Rafael S. Rezende, César Roberto de SouzaICCV 2019 · 424 citations
- Neural-Guided RANSAC: Learning Where to Sample Model HypothesesEric Brachmann, Carsten RotherICCV 2019 · 282 citations
- Quadtree Attention for Vision TransformersShitao Tang, Jiahui Zhang, Siyu Zhu, Ping TanICLR 2022 · 194 citations
- EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose EstimationHansheng Chen, Pichao Wang, Fan Wang, Wei Tian et al.CVPR 2022 · 175 citations
- Expert Sample Consensus Applied to Camera Re-LocalizationEric Brachmann, Carsten RotherICCV 2019 · 136 citations
Related papers
- SANet: Scene Agnostic Network for Camera LocalizationLuwei Yang, Ziqian Bai, Chengzhou Tang, Honghua Li et al.ICCV 2019 · 105 citations
- Learning Camera Localization via Dense Scene MatchingShitao Tang, Chengzhou Tang, Rui Huang, Siyu Zhu et al.CVPR 2021
- R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual LocalizationXudong Jiang, Fangjinhua Wang, Silvano Galliani, Christoph Vogel et al.CVPR 2025
- Hierarchical Scene Coordinate Classification and Regression for Visual LocalizationXiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek et al.CVPR 2020
- Cross-View Visual Geo-Localization for Outdoor Augmented RealityNiluthpol Chowdhury Mithun, Kshitij Minhas, Han-Pang Chiu, Taragay Oskiper et al.IEEE VR 2023 · 22 citations
