SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality
This addresses the need for efficient and high-quality visual localization in augmented reality applications, though it appears incremental as it builds on existing 3D Gaussian splatting techniques.
The paper tackles the problem of visual localization for augmented reality by proposing SplatLoc, which uses 3D Gaussian splatting to enable high-quality rendering and efficient pose estimation with fewer parameters, achieving superior or comparable performance to state-of-the-art methods on two datasets.
Visual localization plays an important role in the applications of Augmented Reality (AR), which enable AR devices to obtain their 6-DoF pose in the pre-build map in order to render virtual content in real scenes. However, most existing approaches can not perform novel view rendering and require large storage capacities for maps. To overcome these limitations, we propose an efficient visual localization method capable of high-quality rendering with fewer parameters. Specifically, our approach leverages 3D Gaussian primitives as the scene representation. To ensure precise 2D-3D correspondences for pose estimation, we develop an unbiased 3D scene-specific descriptor decoder for Gaussian primitives, distilled from a constructed feature volume. Additionally, we introduce a salient 3D landmark selection algorithm that selects a suitable primitive subset based on the saliency score for localization. We further regularize key Gaussian primitives to prevent anisotropic effects, which also improves localization performance. Extensive experiments on two widely used datasets demonstrate that our method achieves superior or comparable rendering and localization performance to state-of-the-art implicit-based visual localization approaches. Project page: \href{https://zju3dv.github.io/splatloc}{https://zju3dv.github.io/splatloc}.