MVL-Loc：利用视觉-语言模型实现可泛化的多场景相机重定位
MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization
AI总结：
本文提出MVL-Loc，一种利用视觉-语言模型预训练知识和多模态数据的端到端多场景6-DoF相机重定位框架，通过自然语言引导多场景学习，在7Scenes和Cambridge Landmarks数据集上取得了最先进性能。
摘要：
相机重定位是现代计算机视觉的一项基础能力，能够从图像中准确确定相机的位置和姿态（6-DoF），对于增强现实（AR）、混合现实（MR）、自动驾驶、配送无人机和机器人导航等应用至关重要。与传统的基于深度学习的方法不同，后者在单一场景中从图像回归相机位姿，往往缺乏在不同环境中的泛化能力和鲁棒性，我们提出了MVL-Loc，一种新颖的端到端多场景6-DoF相机重定位框架。MVL-Loc利用视觉-语言模型（VLMs）中预训练的世界知识，并融合多模态数据，以在室内和室外环境中实现泛化。此外，自然语言被用作一种指令工具来引导多场景学习过程，促进对复杂场景的语义理解并捕捉物体之间的空间关系。在7Scenes和Cambridge Landmarks数据集上的大量实验表明，MVL-Loc在真实世界多场景相机重定位中具有鲁棒性和最先进的性能，在位置和姿态估计方面均提高了精度。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
