# LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2503.23664 · HTML: https://mlsanity.com/paper/2503.23664/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences](https://mlsanity.com/paper/1912.05524/) (2019)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions](https://mlsanity.com/paper/2004.10566/) (2020)
- [3D Registration with Maximal Cliques](https://mlsanity.com/paper/2305.10854/) (2023)
- [EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation](https://mlsanity.com/paper/2303.12787/) (2023)
- [RANSAC-Flow: generic two-stage image alignment](https://mlsanity.com/paper/2004.01526/) (2020)
- [DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points](https://mlsanity.com/paper/2112.06910/) (2021)
- [mathbbXResolution Correspondence Networks](https://mlsanity.com/paper/2012.09842/) (2020)

## Abstract (arXiv)

Visual localization is to estimate the 6-DOF camera pose of a query image in a 3D reference map. We extract keypoints from the reference image and generate a 3D reference map with 3D reconstruction of the keypoints in advance. We emphasize that the more keypoints in the 3D reference map and the smaller the error of the 3D positions of the keypoints, the higher the accuracy of the camera pose estimation. However, previous image-only methods require a huge number of images, and it is difficult to 3D-reconstruct keypoints without error due to inevitable mismatches and failures in feature matching. As a result, the 3D reference map is sparse and inaccurate. In contrast, accurate 3D reference maps can be generated by combining images and 3D sensors. Recently, 3D-LiDAR has been widely used around the world. LiDAR, which measures a large space with high density, has become inexpensive. In addition, accurately calibrated cameras are also widely used, so images that record the external parameters of the camera without errors can be easily obtained. In this paper, we propose a method to directly assign 3D LiDAR point clouds to keypoints to generate dense and accurate 3D reference maps. The proposed method avoids feature matching and achieves accurate 3D reconstruction for almost all keypoints. To estimate camera pose over a wide area, we use the wide-area LiDAR point cloud to remove points that are not visible to the camera and reduce 2D-3D correspondence errors. Using indoor and outdoor datasets, we apply the proposed method to several state-of-the-art local features and confirm that it improves the accuracy of camera pose estimation.