# MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization

arXiv: https://arxiv.org/abs/2507.04509 · HTML: https://mlsanity.com/paper/2507.04509/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 6 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [Image-based localization using LSTMs for structured feature correlation](https://mlsanity.com/paper/1611.07890/) (2016)
- [Modelling Uncertainty in Deep Learning for Camera Relocalization](https://mlsanity.com/paper/1509.05909/) (2015)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Learning Multi-Scene Absolute Pose Regression with Transformers](https://mlsanity.com/paper/2103.11468/) (2021)
- [Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models](https://mlsanity.com/paper/2310.06313/) (2023)
- [AtLoc: Attention Guided Camera Localization](https://mlsanity.com/paper/1909.03557/) (2019)
- [EnvEdit: Environment Editing for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.15685/) (2022)
- [Learning to Generate Scene Graph from Natural Language Supervision](https://mlsanity.com/paper/2109.02227/) (2021)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [Image-based Localization using Hourglass Networks](https://mlsanity.com/paper/1703.07971/) (2017)
- [VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization](https://mlsanity.com/paper/1702.06521/) (2017)
- [Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models](https://mlsanity.com/paper/2407.02482/) (2024)
- [Hybrid Scene Compression for Visual Localization](https://mlsanity.com/paper/1807.07512/) (2018)
- [GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model](https://mlsanity.com/paper/2406.18572/) (2024)
- [FM-Loc: Using Foundation Models for Improved Vision-based Localization](https://mlsanity.com/paper/2304.07058/) (2023)
- [Coarse-to-Fine Multi-Scene Pose Regression with Transformers](https://mlsanity.com/paper/2308.11783/) (2023)
- [CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Maps](https://mlsanity.com/paper/2402.06092/) (2024)
- [EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization](https://mlsanity.com/paper/2402.13537/) (2024)
- [FusionLoc: Camera-2D LiDAR Fusion Using Multi-Head Self-Attention for End-to-End Serving Robot Relocalization](https://mlsanity.com/paper/2303.06872/) (2023)

## Built on by (most cited first, 1 of 1)

- [BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusion](https://mlsanity.com/paper/2601.03713/) (2026)

## Abstract (arXiv)

Camera relocalization, a cornerstone capability of modern computer vision, accurately determines a camera's position and orientation (6-DoF) from images and is essential for applications in augmented reality (AR), mixed reality (MR), autonomous driving, delivery drones, and robotic navigation. Unlike traditional deep learning-based methods that regress camera pose from images in a single scene, which often lack generalization and robustness in diverse environments, we propose MVL-Loc, a novel end-to-end multi-scene 6-DoF camera relocalization framework. MVL-Loc leverages pretrained world knowledge from vision-language models (VLMs) and incorporates multimodal data to generalize across both indoor and outdoor settings. Furthermore, natural language is employed as a directive tool to guide the multi-scene learning process, facilitating semantic understanding of complex scenes and capturing spatial relationships among objects. Extensive experiments on the 7Scenes and Cambridge Landmarks datasets demonstrate MVL-Loc's robustness and state-of-the-art performance in real-world multi-scene camera relocalization, with improved accuracy in both positional and orientational estimates.