MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction


Kunyi Li (Technical University of Munich), Michael Niemeyer (Google), Zeyu Chen (Tsinghua University), Nassir Navab (Technical University of Munich), Federico Tombari (Google)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Accurate meshing from images remains a key challenge in 3D vision. While state-of-the-art 3D Gaussian Splatting (3DGS) methods excel at synthesizing photorealistic novel views through rasterization-based rendering, their reliance on sparse, explicit primitives severely limits their ability to recover watertight and topologically consistent 3D surfaces. We introduce MonoGSDF, a novel method that couples Gaussian-based primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction with monocular RGB images as input. During training, the SDF guides Gaussians' spatial distribution, while at inference, Gaussians serve as priors to reconstruct surfaces, eliminating the need for memory-intensive Marching Cubes. To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization. A multi-resolution training scheme further refines details and monocular geometric cues from off-the-shelf estimators enhance reconstruction quality. Experiments on real-world datasets show MonoGSDF outperforms prior methods while maintaining efficiency.

Citation

@inproceedings{Li_2025_BMVC,
author    = {Kunyi Li and Michael Niemeyer and Zeyu Chen and Nassir Navab and Federico Tombari},
title     = {MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_690/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection