AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
This addresses the challenge of accurate and efficient 3D reconstruction for low-texture regions in indoor and urban scenes, which is incremental by combining prior models with novel representations.
The paper tackles the problem of 3D reconstruction in indoor and urban environments, where existing methods suffer from global inconsistency, discontinuities, or inefficiencies, by proposing an Atlanta-world guided implicit-structured Gaussian Splatting approach that achieves smooth reconstruction while preserving high-frequency details and rendering efficiency, outperforming state-of-the-art methods in quality.
3D reconstruction of indoor and urban environments is a prominent research topic with various downstream applications. However, existing geometric priors for addressing low-texture regions in indoor and urban settings often lack global consistency. Moreover, Gaussian Splatting and implicit SDF fields often suffer from discontinuities or exhibit computational inefficiencies, resulting in a loss of detail. To address these issues, we propose an Atlanta-world guided implicit-structured Gaussian Splatting that achieves smooth indoor and urban scene reconstruction while preserving high-frequency details and rendering efficiency. By leveraging the Atlanta-world model, we ensure the accurate surface reconstruction for low-texture regions, while the proposed novel implicit-structured GS representations provide smoothness without sacrificing efficiency and high-frequency details. Specifically, we propose a semantic GS representation to predict the probability of all semantic regions and deploy a structure plane regularization with learnable plane indicators for global accurate surface reconstruction. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in both indoor and urban scenes, delivering superior surface reconstruction quality.