Summarize this content to 100 words:
[Submitted on 8 Jul 2025 (v1), last revised 11 Feb 2026 (this version, v2)]
View a PDF of the paper titled LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures, by Seungoh Han and 6 other authors
View PDF
HTML (experimental)
Abstract: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: this https URL
Submission history From: Jaehoon Jang [view email] [v1]
Tue, 8 Jul 2025 15:49:53 UTC (9,693 KB)
[v2]
Wed, 11 Feb 2026 13:18:42 UTC (2,795 KB)
