提出高效可微网格，复杂形状重建速度提升显著
DMesh++: An Efficient Differentiable Mesh for Complex Shapes
- 设计新型可微网格结构，将时间复杂度从O(N)降至O(log N)
- 内存占用大幅降低，支持高细节复杂形状处理
- 适用于点云或多视角图像的复杂2D/3D形状重建
近期基于概率的3D三角网格方法通过可微网格连接捕捉多样化形状，但随着形状细节增加，计算开销急剧上升。本文提出一种新的可微网格处理方法，有效应对这一挑战，能高效处理具有复杂结构的网格。该方法将时间复杂度从O(N)降低至O(log N)，且相比以往方法显著减少内存消耗。基于此创新，我们设计了一种重建算法，可从点云或多视角图像中生成复杂的2D与3D形状。项目主页（https://sonsang.github.io/dmesh2-project）提供源代码及补充材料。
原文摘要 · Abstract (English)
Recent probabilistic methods for 3D triangular meshes capture diverse shapes by differentiable mesh connectivity, but face high computational costs with increased shape details. We introduce a new differentiable mesh processing method that addresses this challenge and efficiently handles meshes with intricate structures. Our method reduces time complexity from O(N) to O(log N) and requires significantly less memory than previous approaches. Building on this innovation, we present a reconstruction algorithm capable of generating complex 2D and 3D shapes from point clouds or multi-view images. Visit our project page (https://sonsang.github.io/dmesh2-project) for source code and supplementary material.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。