# AtLoc: Attention Guided Camera Localization

arXiv: https://arxiv.org/abs/1909.03557 · HTML: https://mlsanity.com/paper/1909.03557/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2019.

## Built on by (most cited first, 30 of 92)

- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [Learning Multi-Scene Absolute Pose Regression with Transformers](https://mlsanity.com/paper/2103.11468/) (2021)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments](https://mlsanity.com/paper/2303.09095/) (2023)
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://mlsanity.com/paper/2103.01055/) (2021)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR](https://mlsanity.com/paper/2203.09215/) (2022)
- [Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision](https://mlsanity.com/paper/2104.02538/) (2021)
- [Neural Refinement for Absolute Pose Regression with Feature Synthesis](https://mlsanity.com/paper/2303.10087/) (2023)
- [Visual Localization via Few-Shot Scene Region Classification](https://mlsanity.com/paper/2208.06933/) (2022)
- [CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization](https://mlsanity.com/paper/2103.10796/) (2021)
- [GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2408.11085/) (2024)
- [VS-Net: Voting with Segmentation for Visual Localization](https://mlsanity.com/paper/2105.10886/) (2021)
- [CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data](https://mlsanity.com/paper/2112.09081/) (2021)
- [Camera Pose Auto-Encoders for Improving Pose Regression](https://mlsanity.com/paper/2207.05530/) (2022)
- [UAVScenes: A Multi-Modal Dataset for UAVs](https://mlsanity.com/paper/2507.22412/) (2025)
- [HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion](https://mlsanity.com/paper/2304.00932/) (2023)
- [Reassessing the Limitations of CNN Methods for Camera Pose Regression](https://mlsanity.com/paper/2108.07260/) (2021)
- [RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments](https://mlsanity.com/paper/2211.11238/) (2022)
- [Leveraging Equivariant Features for Absolute Pose Regression](https://mlsanity.com/paper/2204.02163/) (2022)
- [HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation](https://mlsanity.com/paper/2402.14371/) (2024)
- [GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization](https://mlsanity.com/paper/2409.16502/) (2024)
- [SC-wLS: Towards Interpretable Feed-forward Camera Re-localization](https://mlsanity.com/paper/2210.12748/) (2022)
- [SACReg: Scene-Agnostic Coordinate Regression for Visual Localization](https://mlsanity.com/paper/2307.11702/) (2023)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks](https://mlsanity.com/paper/2104.07196/) (2021)
- [Coarse-to-Fine Multi-Scene Pose Regression with Transformers](https://mlsanity.com/paper/2308.11783/) (2023)
- [Paying Attention to Activation Maps in Camera Pose Regression](https://mlsanity.com/paper/2103.11477/) (2021)
- [LightLoc: Learning Outdoor LiDAR Localization at Light Speed](https://mlsanity.com/paper/2503.17814/) (2025)
- [Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization](https://mlsanity.com/paper/2507.23569/) (2025)

## Abstract (arXiv)

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.