# Efficient Scene Compression for Visual-based Localization

arXiv: https://arxiv.org/abs/2011.13894 · HTML: https://mlsanity.com/paper/2011.13894/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [Is Geometry Enough for Matching in Visual Localization?](https://mlsanity.com/paper/2203.12979/) (2022)
- [SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality](https://mlsanity.com/paper/2409.14067/) (2024)
- [Camera Pose Auto-Encoders for Improving Pose Regression](https://mlsanity.com/paper/2207.05530/) (2022)
- [NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization](https://mlsanity.com/paper/2211.11177/) (2022)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [SACReg: Scene-Agnostic Coordinate Regression for Visual Localization](https://mlsanity.com/paper/2307.11702/) (2023)
- [Differentiable Product Quantization for Memory Efficient Camera Relocalization](https://mlsanity.com/paper/2407.15540/) (2024)
- [Fast and Lightweight Scene Regressor for Camera Relocalization](https://mlsanity.com/paper/2212.01830/) (2022)
- [Long-term Visual Map Sparsification with Heterogeneous GNN](https://mlsanity.com/paper/2203.15182/) (2022)
- [egenioussBench: A New Dataset for Geospatial Visual Localisation](https://mlsanity.com/paper/2605.05351/) (2026)
- [Efficient Map Sparsification Based on 2D and 3D Discretized Grids](https://mlsanity.com/paper/2303.10882/) (2023)
- [LocoNeRF: A NeRF-based Approach for Local Structure from Motion for Precise Localization](https://mlsanity.com/paper/2310.05134/) (2023)

## Abstract (arXiv)

Estimating the pose of a camera with respect to a 3D reconstruction or scene representation is a crucial step for many mixed reality and robotics applications. Given the vast amount of available data nowadays, many applications constrain storage and/or bandwidth to work efficiently. To satisfy these constraints, many applications compress a scene representation by reducing its number of 3D points. While state-of-the-art methods use K-cover-based algorithms to compress a scene, they are slow and hard to tune. To enhance speed and facilitate parameter tuning, this work introduces a novel approach that compresses a scene representation by means of a constrained quadratic program (QP). Because this QP resembles a one-class support vector machine, we derive a variant of the sequential minimal optimization to solve it. Our approach uses the points corresponding to the support vectors as the subset of points to represent a scene. We also present an efficient initialization method that allows our method to converge quickly. Our experiments on publicly available datasets show that our approach compresses a scene representation quickly while delivering accurate pose estimates.