VRS-NeRF：基于稀疏神经辐射场的视觉重定位
VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field
AI总结：
针对现有视觉重定位方法精度与效率难以兼顾的问题，提出基于稀疏神经辐射场的VRS-NeRF框架，结合显式几何地图与隐式学习地图，在保证接近分层方法精度的同时大幅提升效率、减小地图体积。
摘要：
视觉重定位是自动驾驶、机器人技术以及虚拟/增强现实领域的关键技术。经过数十年的探索，绝对位姿回归（APR）、场景坐标回归（SCR）以及分层方法（HMs）已成为最主流的框架。然而，APR和SCR虽然效率较高，但精度有限，在大规模室外场景中尤为明显；HMs精度较高，但需要存储大量2D描述子用于匹配，导致效率低下。本文提出了一种高效且精准的视觉重定位框架VRS-NeRF，该框架基于稀疏神经辐射场实现。具体而言，我们引入了用于三维地图表示的显式几何地图（EGM），以及用于稀疏斑块渲染的隐式学习地图（ILM）。在定位过程中，EGM提供稀疏二维点的先验信息，ILM利用这些稀疏点，通过稀疏NeRF渲染待匹配的斑块。这一设计使我们无需存储大量二维描述子，从而减小了地图体积。此外，我们仅针对有效点渲染斑块，而非对整幅图像的所有像素进行渲染，大幅缩短了渲染时间。该框架继承了HMs的高精度，同时规避了其效率低下的问题。在7Scenes、CambridgeLandmarks以及Aachen数据集上的实验表明，本文方法的精度远优于APR和SCR，性能与HMs接近，但效率要高得多。
英文摘要：
Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordinate regression (SCR), and hierarchical methods (HMs) have become the most popular frameworks. However, in spite of high efficiency, APRs and SCRs have limited accuracy especially in large-scale outdoor scenes; HMs are accurate but need to store a large number of 2D descriptors for matching, resulting in poor efficiency. In this paper, we propose an efficient and accurate framework, called VRS-NeRF, for visual relocalization with sparse neural radiance field. Precisely, we introduce an explicit geometric map (EGM) for 3D map representation and an implicit learning map (ILM) for sparse patches rendering. In this localization process, EGP provides priors of spare 2D points and ILM utilizes these sparse points to render patches with sparse NeRFs for matching. This allows us to discard a large number of 2D descriptors so as to reduce the map size. Moreover, rendering patches only for useful points rather than all pixels in the whole image reduces the rendering time significantly. This framework inherits the accuracy of HMs and discards their low efficiency. Experiments on 7Scenes, CambridgeLandmarks, and Aachen datasets show that our method gives much better accuracy than APRs and SCRs, and close performance to HMs but is much more efficient.
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。
