# Local Supports Global: Deep Camera Relocalization with Sequence Enhancement

arXiv: https://arxiv.org/abs/1908.04391 · HTML: https://mlsanity.com/paper/1908.04391/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2019.

## Built on by (most cited first, 25 of 25)

- [The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs](https://mlsanity.com/paper/2208.08988/) (2022)
- [Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision](https://mlsanity.com/paper/2104.02538/) (2021)
- [Learning Camera Localization via Dense Scene Matching](https://mlsanity.com/paper/2103.16792/) (2021)
- [SFD2: Semantic-guided Feature Detection and Description](https://mlsanity.com/paper/2304.14845/) (2023)
- [HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer](https://mlsanity.com/paper/2305.03595/) (2023)
- [RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments](https://mlsanity.com/paper/2211.11238/) (2022)
- [SC-wLS: Towards Interpretable Feed-forward Camera Re-localization](https://mlsanity.com/paper/2210.12748/) (2022)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Coarse-to-Fine Multi-Scene Pose Regression with Transformers](https://mlsanity.com/paper/2308.11783/) (2023)
- [IMP: Iterative Matching and Pose Estimation with Adaptive Pooling](https://mlsanity.com/paper/2304.14837/) (2023)
- [Scene-agnostic Pose Regression for Visual Localization](https://mlsanity.com/paper/2503.19543/) (2025)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion](https://mlsanity.com/paper/2111.12927/) (2021)
- [Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer](https://mlsanity.com/paper/2512.21883/) (2025)
- [TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation](https://mlsanity.com/paper/2105.14065/) (2021)
- [Objects Matter: Learning Object Relation Graph for Robust Camera Relocalization](https://mlsanity.com/paper/2205.13280/) (2022)
- [ConDo: Continual Domain Expansion for Absolute Pose Regression](https://mlsanity.com/paper/2412.13452/) (2024)
- [HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset](https://mlsanity.com/paper/2303.02610/) (2023)
- [Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Cameras](https://mlsanity.com/paper/2312.00500/) (2023)
- [VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field](https://mlsanity.com/paper/2404.09271/) (2024)
- [Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video](https://mlsanity.com/paper/2203.12804/) (2022)
- [S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization](https://mlsanity.com/paper/2205.05861/) (2022)
- [PRAM: Place Recognition Anywhere Model for Efficient Visual Localization](https://mlsanity.com/paper/2404.07785/) (2024)
- [From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization](https://mlsanity.com/paper/2602.03198/) (2026)
- [Temporal-Aware Fusion for Robust Outdoor LiDAR Localization](https://mlsanity.com/paper/2609.36432/) (2026)

## Abstract (arXiv)

We propose to leverage the local information in image sequences to support global camera relocalization. In contrast to previous methods that regress global poses from single images, we exploit the spatial-temporal consistency in sequential images to alleviate uncertainty due to visual ambiguities by incorporating a visual odometry (VO) component. Specifically, we introduce two effective steps called content-augmented pose estimation and motion-based refinement. The content-augmentation step focuses on alleviating the uncertainty of pose estimation by augmenting the observation based on the co-visibility in local maps built by the VO stream. Besides, the motion-based refinement is formulated as a pose graph, where the camera poses are further optimized by adopting relative poses provided by the VO component as additional motion constraints. Thus, the global consistency can be guaranteed. Experiments on the public indoor 7-Scenes and outdoor Oxford RobotCar benchmark datasets demonstrate that benefited from local information inherent in the sequence, our approach outperforms state-of-the-art methods, especially in some challenging cases, e.g., insufficient texture, highly repetitive textures, similar appearances, and over-exposure.