# Hybrid Scene Compression for Visual Localization

arXiv: https://arxiv.org/abs/1807.07512 · HTML: https://mlsanity.com/paper/1807.07512/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 30 of 40)

- [Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses](https://mlsanity.com/paper/2305.14059/) (2023)
- [OrienterNet: Visual Localization in 2D Public Maps with Neural Matching](https://mlsanity.com/paper/2304.02009/) (2023)
- [Is Geometry Enough for Matching in Visual Localization?](https://mlsanity.com/paper/2203.12979/) (2022)
- [GLACE: Global Local Accelerated Coordinate Encoding](https://mlsanity.com/paper/2406.04340/) (2024)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision](https://mlsanity.com/paper/2104.02538/) (2021)
- [The NeRFect Match: Exploring NeRF Features for Visual Localization](https://mlsanity.com/paper/2403.09577/) (2024)
- [VS-Net: Voting with Segmentation for Visual Localization](https://mlsanity.com/paper/2105.10886/) (2021)
- [NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization](https://mlsanity.com/paper/2211.11177/) (2022)
- [How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines](https://mlsanity.com/paper/2103.05086/) (2021)
- [DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching](https://mlsanity.com/paper/2306.12547/) (2023)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [FocusTune: Tuning Visual Localization through Focus-Guided Sampling](https://mlsanity.com/paper/2311.02872/) (2023)
- [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)
- [LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment](https://mlsanity.com/paper/2410.12269/) (2024)
- [Learning to Produce Semi-dense Correspondences for Visual Localization](https://mlsanity.com/paper/2402.08359/) (2024)
- [Differentiable Product Quantization for Memory Efficient Camera Relocalization](https://mlsanity.com/paper/2407.15540/) (2024)
- [ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training](https://mlsanity.com/paper/2510.11605/) (2025)
- [Privacy-Preserving Representations are not Enough -- Recovering Scene Content from Camera Poses](https://mlsanity.com/paper/2305.04603/) (2023)
- [GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations](https://mlsanity.com/paper/2508.18242/) (2025)
- [ImPosing: Implicit Pose Encoding for Efficient Visual Localization](https://mlsanity.com/paper/2205.02638/) (2022)
- [Fast and Lightweight Scene Regressor for Camera Relocalization](https://mlsanity.com/paper/2212.01830/) (2022)
- [A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera Relocalization](https://mlsanity.com/paper/2502.20036/) (2025)
- [Learning to Predict Repeatability of Interest Points](https://mlsanity.com/paper/2105.03578/) (2021)
- [Long-term Visual Map Sparsification with Heterogeneous GNN](https://mlsanity.com/paper/2203.15182/) (2022)
- [Learning to Structure an Image with Few Colors and Beyond](https://mlsanity.com/paper/2208.08438/) (2022)
- [Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer](https://mlsanity.com/paper/2212.03434/) (2022)
- [MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization](https://mlsanity.com/paper/2507.04509/) (2025)
- [ImLoc: Revisiting Visual Localization with Image-based Representation](https://mlsanity.com/paper/2601.04185/) (2026)

## Abstract (arXiv)

Localizing an image wrt. a 3D scene model represents a core task for many computer vision applications. An increasing number of real-world applications of visual localization on mobile devices, e.g., Augmented Reality or autonomous robots such as drones or self-driving cars, demand localization approaches to minimize storage and bandwidth requirements. Compressing the 3D models used for localization thus becomes a practical necessity. In this work, we introduce a new hybrid compression algorithm that uses a given memory limit in a more effective way. Rather than treating all 3D points equally, it represents a small set of points with full appearance information and an additional, larger set of points with compressed information. This enables our approach to obtain a more complete scene representation without increasing the memory requirements, leading to a superior performance compared to previous compression schemes. As part of our contribution, we show how to handle ambiguous matches arising from point compression during RANSAC. Besides outperforming previous compression techniques in terms of pose accuracy under the same memory constraints, our compression scheme itself is also more efficient. Furthermore, the localization rates and accuracy obtained with our approach are comparable to state-of-the-art feature-based methods, while using a small fraction of the memory.