MeshSplat: 通过高斯散射实现通用稀疏视图表面重建
MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
AI总结：
MeshSplat通过高斯散射实现稀疏视图下的通用表面重建，利用2DGS连接新视图合成与几何先验，提升重建精度。
摘要：
表面重建在计算机视觉和图形学中已被广泛研究。然而，现有表面重建工作在输入视图极度稀疏时难以恢复准确的场景几何。为了解决这一问题，我们提出了MeshSplat，一种通过高斯散射实现的通用稀疏视图表面重建框架。我们的核心思想是利用2DGS作为桥梁，将新视图合成与学习的几何先验连接起来，然后将这些先验转移到表面重建中。具体来说，我们引入了一个前馈网络来预测每视图像素对齐的2DGS，这使网络能够合成新视图图像，从而消除了对直接3D真实监督的需求。为了提高2DGS位置和方向预测的准确性，我们提出了一种加权配准损失来正则化深度图，特别是在输入视图的重叠区域，还提出了一种法线预测网络来对齐2DGS的方向与由单目法线估计器预测的法线向量。大量实验验证了我们所提出改进的有效性，证明我们的方法在通用稀疏视图网格重建任务中实现了最先进的性能。项目页面：https://hanzhichang.github.io/meshsplat_web
英文摘要：
Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the input views are extremely sparse. To address this issue, we propose MeshSplat, a generalizable sparse-view surface reconstruction framework via Gaussian Splatting. Our key idea is to leverage 2DGS as a bridge, which connects novel view synthesis to learned geometric priors and then transfers these priors to achieve surface reconstruction. Specifically, we incorporate a feed-forward network to predict per-view pixel-aligned 2DGS, which enables the network to synthesize novel view images and thus eliminates the need for direct 3D ground-truth supervision. To improve the accuracy of 2DGS position and orientation prediction, we propose a Weighted Chamfer Distance Loss to regularize the depth maps, especially in overlapping areas of input views, and also a normal prediction network to align the orientation of 2DGS with normal vectors predicted by a monocular normal estimator. Extensive experiments validate the effectiveness of our proposed improvement, demonstrating that our method achieves state-of-the-art performance in generalizable sparse-view mesh reconstruction tasks. Project Page: https://hanzhichang.github.io/meshsplat_web
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。
