# $L^3$:Scene-agnostic Visual Localization in the Wild

Source: [$L^3$:Scene-agnostic Visual Localization in the Wild](<https://www.sota2.com/research/paper/69afa5932d603e6de3e43bbe>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-11T05:00:11.798Z

Authors: Yu Zhang, Muhua Zhu, Yifei Xue, Tie Ji, Yizhen Lao

Published: 2026-03-09T04:04:24.000Z

## Abstract

Standard visual localization methods typically require offline pre-processing of scenes to obtain 3D structural information for better performance. This inevitably introduces additional computational and time costs, as well as the overhead of storing scene representations. Can we visually localize in a wild scene without any off-line preprocessing step? In this paper, we leverage the online inference capabilities of feed-forward 3D reconstruction networks to propose a novel map-free visual localization framework $L^3$. Specifically, by performing direct online 3D reconstruction on RGB images, followed by two-stage metric scale recovery and pose refinement based on 2D-3D correspondences, $L^3$ achieves high accuracy without the need to pre-build or store any offline scene representations. Extensive experiments demonstrate $L^3$ not only that the performance is comparable to state-of-the-art solutions on various benchmarks, but also that it exhibits significantly superior robustness in sparse scenes (fewer reference images per scene).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Visual Localization on Cambridge Landmarks (Scene-wise Median Error)](<https://www.sota2.com/research/sota/visual-localization-on-cambridge-landmarks-scene-wise-median-error.md>): Visual Localization; Cambridge Landmarks; Kings Median Translation Error (cm): 13.

- [Visual Localization on 7Scenes](<https://www.sota2.com/research/sota/visual-localization-on-7scenes.md>): Visual Localization; 7Scenes; Median Translation Error (cm) - Chess: 0.6.

- [Visual Localization on 12Scenes](<https://www.sota2.com/research/sota/visual-localization-on-12scenes.md>): Visual Localization; 12Scenes; Average Median Translation Error (cm): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.07937>)

[PDF](<https://arxiv.org/pdf/2603.07937.pdf>)
