基于绕数法向一致性的快速全局一致法向定向
Fast and Globally Consistent Normal Orientation based on the Winding Number Normal Consistency
AI总结:
针对点云全局一致法向定向难题,提出绕数法向一致性新性质,结合参数化高斯重建目标函数构建迭代算法,可借助树码近似加速,速度显著优于现有最优方法,代码已集成PyTorch并开源。
摘要:
为点云估计方向一致的法向可支撑计算机图形学中的诸多重要应用。尽管借助PCA(主成分分析)等简单技术即可完成局部法向估计,但将其调整为全局一致的方向一直是公认的难题。近期部分方法利用绕数公式的多种性质实现全局一致性,虽取得了显著进展,但这类算法要么时空复杂度较高,要么无法针对含缺陷数据生成准确且方向一致的法向。本文提出绕数公式的一项新性质——绕数法向一致性(Winding Number Normal Consistency,WNNC),以解决该问题。该性质源于一项简单观测:从绕数场采样得到的法向(负梯度)应与用于计算绕数场的法向方向一致。由于WNNC性质本身无法解决内/外方向的二义性问题,我们进一步引入了参数化高斯重建(Parametric Gauss Reconstruction,PGR)的目标函数。我们提出通过交替执行基于WNNC的法向更新与基于PGR的梯度下降来迭代更新法向,由此得到一种极其简洁却有效的迭代算法,可快速高质量收敛至全局一致的法向。此外,本文提出的算法仅需重复计算绕数公式及其导数,可通过基于树码的近似算法实现加速与并行化。我们的GPU(甚至CPU)实现版本,在原始点云法向定向任务上的速度远快于当前最先进的方法。我们的代码已集成至主流PyTorch框架,以推动绕数相关的后续研究,代码公开地址为https://jsnln.github.io/wnnc/index.html。
英文摘要:
Estimating consistently oriented normals for point clouds enables a number of important applications in computer graphics. While local normal estimation is possible with simple techniques like PCA, orienting them to be globally consistent has been a notoriously difficult problem. Some recent methods exploit various properties of the winding number formula to achieve global consistency. Despite their exciting progress, these algorithms either have high space/time complexity, or do not produce accurate and consistently oriented normals for imperfect data. In this paper, we propose a novel property from the winding number formula, termed Winding Number Normal Consistency (WNNC), to tackle this problem. The derived property is based on the simple observation that the normals (negative gradients) sampled from the winding number field should be codirectional to the normals used to compute the winding number field. Since the WNNC property itself does not resolve the inside/outside orientation ambiguity, we further incorporate an objective function from Parametric Gauss Reconstruction (PGR). We propose to iteratively update normals by alternating between WNNC-based normal updates and PGR-based gradient descents, which leads to an embarrassingly simple yet effective iterative algorithm that allows fast and high-quality convergence to globally consistent normals. Furthermore, our proposed algorithm only involves repeatedly evaluating the winding number formula and its derivatives, which can be accelerated and parallelized using a treecode-based approximation algorithm. Our GPU (and even CPU) implementation can be significantly faster than the recent state-of-the-art methods for normal orientation from raw points. Our code is integrated with the popular PyTorch framework to facilitate further research into winding numbers, and is publicly available at https://jsnln.github.io/wnnc/index.html.
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。