HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset
Abstract
In this work, we propose HyperPose, which utilizes hypernetworks in absolute camera pose regressors. The inherent appearance variations in natural scenes, attributable to environmental conditions, perspective, and lighting, induce a significant domain disparity between the training and test datasets. This disparity degrades the precision of contemporary localization networks. To mitigate this, we advocate for incorporating hypernetworks into single-scene and multiscene camera pose regression models. During inference, the hypernetwork dynamically computes adaptive weights for the localization regression heads based on the particular input image, effectively narrowing the domain gap. Using indoor and outdoor datasets, we evaluate the HyperPose methodology across multiple established absolute pose regression architectures. We also introduce and share the Extended Cambridge Landmarks (ECL), a novel localization dataset, based on the Cambridge Landmarks dataset, showing it in multiple seasons with significantly varying appearance conditions. Our empirical experiments demonstrate that HyperPose yields notable performance enhancements for single-and multi-scene architectures. We have made our source code, pre-trained models 1 , and the ECL dataset openly available 2 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- 3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Early Convolutions Help Transformers See Better cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Early Convolutions Help Transformers See Better cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Cited by top-tier papers2
- 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
- Simple but Effective Triplet-Based Compression Strategies for Compact Visual LocalizationTorsten Sattler, Zuzana KukelovaCVPR 2026
Builds on21
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 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
- Implicit Neural Representations with Periodic Activation FunctionsVincent Sitzmann, Julien N. P. Martel, Alexander W. Bergman, David B. Lindell et al.NeurIPS 2020 · 4,008 citations
- Early Convolutions Help Transformers See BetterTete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell et al.NeurIPS 2021 · 974 citations
- Continual learning with hypernetworksJohannes von Oswald, Christian Henning, João Sacramento, Benjamin F. GreweICLR 2020 · 412 citations
Related papers
- Learning Multi-Scene Absolute Pose Regression with TransformersYoli Shavit, Ron Ferens, Yosi KellerICCV 2021 · 163 citations
- Map-Relative Pose Regression for Visual Re-LocalizationShuai Chen, Tommaso Cavallari, Victor Adrian Prisacariu, Eric BrachmannCVPR 2024
- Adversarial Exploitation of Data Diversity Improves Visual LocalizationSihang Li, Siqi Tan, Bowen Chang, Jing Zhang et al.ICCV 2025 · 4 citations
- ConDo: Continual Domain Expansion for Absolute Pose RegressionZijun Li, Zhipeng Cai, Bochun Yang, Xuelun Shen et al.AAAI 2025 · 2 citations
- Hierarchical Scene Coordinate Classification and Regression for Visual LocalizationXiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek et al.CVPR 2020
