# Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?

arXiv: https://arxiv.org/abs/2507.18881 · HTML: https://mlsanity.com/paper/2507.18881/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 59 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (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)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration](https://mlsanity.com/paper/1604.01093/) (2016)
- [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://mlsanity.com/paper/2210.10770/) (2022)
- [OrienterNet: Visual Localization in 2D Public Maps with Neural Matching](https://mlsanity.com/paper/2304.02009/) (2023)
- [Particle Filter Networks with Application to Visual Localization](https://mlsanity.com/paper/1805.08975/) (2018)
- [Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2404.01943/) (2024)
- [Renderable Neural Radiance Map for Visual Navigation](https://mlsanity.com/paper/2303.00304/) (2023)
- [Curious Representation Learning for Embodied Intelligence](https://mlsanity.com/paper/2105.01060/) (2021)
- [LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments](https://mlsanity.com/paper/2104.09169/) (2021)
- [SPA: 3D Spatial-Awareness Enables Effective Embodied Representation](https://mlsanity.com/paper/2410.08208/) (2024)
- [Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network](https://mlsanity.com/paper/1903.01804/) (2019)
- [LASER: LAtent SpacE Rendering for 2D Visual Localization](https://mlsanity.com/paper/2204.00157/) (2022)
- [F3Loc: Fusion and Filtering for Floorplan Localization](https://mlsanity.com/paper/2403.03370/) (2024)
- [FloNa: Floor Plan Guided Embodied Visual Navigation](https://mlsanity.com/paper/2412.18335/) (2024)
- [SeDAR - Semantic Detection and Ranging: Humans can localise without LiDAR, can robots?](https://mlsanity.com/paper/1709.01500/) (2017)
- [Self-Supervised Image Representation Learning with Geometric Set Consistency](https://mlsanity.com/paper/2203.15361/) (2022)

## Built on by (most cited first, 4 of 4)

- [Perspective from a Broader Context: Can Room Style Knowledge Help Visual Floorplan Localization?](https://mlsanity.com/paper/2508.01216/) (2025)
- [DisCo-FLoc: Semantic-Free Floorplan Localization via SE(2)-Aware Contrastive Disambiguation](https://mlsanity.com/paper/2601.01822/) (2026)
- [From Uncertainty to Determinism: Coarse-to-Fine Visual Floorplan Localization without Ray Matching](https://mlsanity.com/paper/2607.26817/) (2026)
- [GALoc: Gravity Aligned Wireframes for Depth-Free Monocular Floorplan Localization](https://mlsanity.com/paper/2609.08385/) (2026)

## Abstract (arXiv)

Since a building's floorplans are easily accessible, consistent over time, and inherently robust to changes in visual appearance, self-localization within the floorplan has attracted researchers' interest. However, since floorplans are minimalist representations of a building's structure, modal and geometric differences between visual perceptions and floorplans pose challenges to this task. While existing methods cleverly utilize 2D geometric features and pose filters to achieve promising performance, they fail to address the localization errors caused by frequent visual changes and view occlusions due to variously shaped 3D objects. To tackle these issues, this paper views the 2D Floorplan Localization (FLoc) problem from a higher dimension by injecting 3D geometric priors into the visual FLoc algorithm. For the 3D geometric prior modeling, we first model geometrically aware view invariance using multi-view constraints, i.e., leveraging imaging geometric principles to provide matching constraints between multiple images that see the same points. Then, we further model the view-scene aligned geometric priors, enhancing the cross-modal geometry-color correspondences by associating the scene's surface reconstruction with the RGB frames of the sequence. Both 3D priors are modeled through self-supervised contrastive learning, thus no additional geometric or semantic annotations are required. These 3D priors summarized in extensive realistic scenes bridge the modal gap while improving localization success without increasing the computational burden on the FLoc algorithm. Sufficient comparative studies demonstrate that our method significantly outperforms state-of-the-art methods and substantially boosts the FLoc accuracy. All data and code will be released after the anonymous review.