基于高保真表面点云的多视角图像三维重建
High-Fidelity Surface Splatting-Based 3D Reconstruction from Multi-View Images
AI总结：
本文提出改进的隐式移动最小二乘方法，通过紧凑多项式核和随机正则化提升多视角图像的高频率几何重建精度和渲染质量。
摘要：
多视角网格重建仍是计算机图形学和视觉领域的核心挑战，尤其在从稀疏观测中恢复高频几何方面。最近的方法如3D高斯点云 (3DGS) 和神经辐射场 (NeRF) 依赖后期处理提取网格，从而限制了几何和外观的联合优化。隐式移动最小二乘 (IMLS) 代替直接将点云转换为有符号距离和纹理场，支持端到端的重建和渲染。然而，现有IMLS公式使用指数核，在高频细节方面表现不佳。我们引入具有局部支持的紧凑多项式核，具有更大的灵活性，允许更好地控制频率内容和改进的几何保真度。为进一步增强细节，我们结合随机正则化与拉普拉斯滤波。共同，这些改进在保持稳定优化的同时，提高了高频结构的保持。实验显示在表面重建和渲染中均达到最先进的性能，从多视角数据中产生更准确的几何和更清晰的视觉效果。
英文摘要：
Multi-view mesh reconstruction remains a core challenge in computer graphics and vision, especially for recovering high-frequency geometry from sparse observations. Recent methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) rely on post-processing for mesh extraction, thereby limiting joint optimization of geometry and appearance. Implicit Moving Least Squares (IMLS) instead enables direct conversion of point clouds into signed distance and texture fields, supporting end-to-end reconstruction and rendering. However, existing IMLS formulations use exponential kernels that struggle with high-frequency detail. We introduce a compact polynomial kernel with local support and greater flexibility, allowing better control over frequency content and improved geometric fidelity. To further enhance fine details, we incorporate stochastic regularization with Laplacian filtering. Together, these improve the preservation of high-frequency structure while maintaining stable optimization. Experiments show state-of-the-art performance in both surface reconstruction and rendering, yielding more accurate geometry and sharper visuals from multi-view data.
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。
