NeuSG：基于 3D Gaussian Splatting 引导的神经隐式表面重建
NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance
AI总结：
本文提出 NeuSG，通过尺度正则化与表面法向先验细化 3D Gaussian Splatting 点云，并联合优化神经隐式模型，实现细节丰富的多视图表面重建。
摘要：
现有的神经隐式表面重建方法通过利用深度图或点云等显式几何先验作为正则化，在多视图三维重建中取得了令人瞩目的性能。然而，由于深度图过度平滑或点云稀疏，重建结果仍然缺乏精细细节。在本文中，我们提出了一种由 3D Gaussian Splatting 引导的神经隐式表面重建流程，以恢复高度细致的表面。3D Gaussian Splatting 的优势在于它能够生成具有详细结构的稠密点云。尽管如此，直接采用 3D Gaussian Splatting 可能会失败，因为生成的点是三维高斯的中心，而这些中心并不一定位于表面上。因此，我们引入了一个尺度正则化器，通过强制三维高斯变得极薄，将其中心拉向表面。此外，我们提出利用神经隐式模型预测的表面法向先验来细化来自 3D Gaussian Splatting 的点云，而不是使用固定的点集作为引导。因此，在更准确的 3D Gaussian Splatting 引导下，表面重建质量得到提升。通过联合优化 3D Gaussian Splatting 和神经隐式模型，我们的方法同时受益于两种表示，并生成具有复杂细节的完整表面。在 Tanks and Temples 上的实验验证了所提方法的有效性。
英文摘要：
Existing neural implicit surface reconstruction methods have achieved impressive performance in multi-view 3D reconstruction by leveraging explicit geometry priors such as depth maps or point clouds as regularization. However, the reconstruction results still lack fine details because of the over-smoothed depth map or sparse point cloud. In this work, we propose a neural implicit surface reconstruction pipeline with guidance from 3D Gaussian Splatting to recover highly detailed surfaces. The advantage of 3D Gaussian Splatting is that it can generate dense point clouds with detailed structure. Nonetheless, a naive adoption of 3D Gaussian Splatting can fail since the generated points are the centers of 3D Gaussians that do not necessarily lie on the surface. We thus introduce a scale regularizer to pull the centers close to the surface by enforcing the 3D Gaussians to be extremely thin. Moreover, we propose to refine the point cloud from 3D Gaussians Splatting with the normal priors from the surface predicted by neural implicit models instead of using a fixed set of points as guidance. Consequently, the quality of surface reconstruction improves from the guidance of the more accurate 3D Gaussian splatting. By jointly optimizing the 3D Gaussian Splatting and the neural implicit model, our approach benefits from both representations and generates complete surfaces with intricate details. Experiments on Tanks and Temples verify the effectiveness of our proposed method.
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。
