AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians

Moreover, Gaussian Splatting and implicit SDF fields often suffer from discontinuities or exhibit computational inefficiencies, resulting in a loss of detail. T Gaussian o address Splatting these issues, that achie we propose ves smooth an Atlanta-w indoor and orld urban guided scene implicit-structured reconstruction while preserving high-frequency details and rendering efficiency. By leveraging the Atlanta-world model, we ensure the accurate surface reconstruction for low-texture re smoothness gions, while without the proposed sacrificing nov ef el ficienc implicit-structured y and high-frequenc GS representations y details. Specifically provide, 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 that global our method accurate outperforms surface reconstruction.