用手机拍全景图也能生成逼真3D场景，关键靠墙面结构和相机姿态约束。
LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures
- 利用手机拍摄时的粗略位姿和单目深度，结合室内平面结构初始化点云。
- 在纹理缺失的室内场景中实现稳定优化，重建精度显著优于现有方法。
- 适合移动端全景重建、虚拟场景摆放等应用，无需专业设备。
我们提出 LighthouseGS，一种基于 3D Gaussian Splatting 的实用新视角合成框架，仅需单个移动设备的简单全景式拍摄即可完成重建。由于以旋转为主、基线狭窄，且在纹理缺失的室内场景中，相机位姿与3D点估计难度大。为此，LighthouseGS 利用粗略几何先验（如设备相机位姿和单目深度估计）以及室内平面结构，提出一种名为平面支架构建的新初始化方法，在结构上生成一致的3D点；随后采用稳定的剪枝策略提升几何精度与优化稳定性。此外，引入几何与光度校正，解决移动设备运动漂移与自动曝光带来的不一致性。在真实与合成室内场景上测试，LighthouseGS 实现了逼真的渲染效果，超越当前最先进方法，支持全景视图合成与物体放置等应用。
原文摘要 · Abstract (English)
We introduce LighthouseGS, a practical novel view synthesis framework based on 3D Gaussian Splatting that utilizes simple panorama-style captures from a single mobile device. While convenient, this rotation-dominant motion and narrow baseline make accurate camera pose and 3D point estimation challenging, especially in textureless indoor scenes. To address these challenges, LighthouseGS leverages rough geometric priors, such as mobile device camera poses and monocular depth estimation, and utilizes indoor planar structures. Specifically, we propose a new initialization method called plane scaffold assembly to generate consistent 3D points on these structures, followed by a stable pruning strategy to enhance geometry and optimization stability. Additionally, we present geometric and photometric corrections to resolve inconsistencies from motion drift and auto-exposure in mobile devices. Tested on real and synthetic indoor scenes, LighthouseGS delivers photorealistic rendering, outperforming state-of-the-art methods and enabling applications like panoramic view synthesis and object placement. Project page: https://vision3d-lab.github.io/lighthousegs/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。