MonoGSDF：探索单目几何线索用于高斯点扩散引导的隐式表面重建
MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction
AI总结：
MonoGSDF通过结合高斯点与神经SDF，利用单目几何线索实现高效隐式表面重建，提升三维表面恢复的精度与效率。
摘要：
单目图像生成精确网格仍然是三维视觉中的关键挑战。尽管最先进的三维高斯点扩散（3DGS）方法通过基于光栅化的渲染技术在合成逼真新视角方面表现出色，但其对稀疏、显式原始语义的依赖严重限制了其恢复封闭且拓扑一致的三维表面的能力。我们引入了MonoGSDF，一种将基于高斯的原始语义与神经符号距离场（SDF）相结合的新方法，以实现高质量的重建。在训练过程中，SDF指导高斯点的空间分布，而在推理过程中，高斯点作为先验用于重建表面，消除了对内存密集型Marching Cubes的依赖。为处理任意尺度的场景，我们提出了一种鲁棒的缩放策略以实现稳健的泛化。多分辨率训练方案进一步细化细节，并且从现成的估计器中增强单目几何线索以提高重建质量。在真实世界数据集上的实验表明，MonoGSDF在保持效率的同时优于先前的方法。
英文摘要：
Accurate meshing from monocular 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. 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
