Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations
Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations
复制标题
DOI：
10.1109/cvpr46437.2021.00044
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Yifan Wang;Shihao Wu;A. C. Öztireli;O. Sorkine-Hornung
中科院分区：
文献类型：
--
作者：
Yifan Wang;Shihao Wu;A. C. Öztireli;O. Sorkine-Hornung
神经隐式函数已成为 3D 表面的强大表示。这样的函数可以将具有复杂细节的高质量表面编码为深度神经网络的参数。然而，优化参数以实现准确和稳健的重建仍然是一个挑战，特别是当输入数据有噪声或不完整时。在这项工作中，我们开发了一种混合神经表面表示，使我们能够实施几何感知采样和正则化，从而显着提高重建的保真度。我们建议使用等值点作为神经隐式函数的显式表示。这些点在训练期间实时计算和更新，以捕获重要的几何特征并对优化施加几何约束。我们证明，我们的方法可以用于改进从多视图图像或点云重建神经隐式表面的最先进技术。定量和定性评估表明，与现有的采样和优化方法相比，我们的方法可以实现更快的收敛、更好的泛化以及细节和拓扑的准确恢复。
Neural implicit functions have emerged as a powerful representation for surfaces in 3D. Such a function can en-code a high quality surface with intricate details into the parameters of a deep neural network. However, optimizing for the parameters for accurate and robust reconstructions remains a challenge, especially when the input data is noisy or incomplete. In this work, we develop a hybrid neural surface representation that allows us to impose geometry-aware sampling and regularization, which significantly improves the fidelity of reconstructions. We propose to use iso-points as an explicit representation for a neural implicit function. These points are computed and updated on-the-fly during training to capture important geometric features and impose geometric constraints on the optimization. We demonstrate that our method can be adopted to improve state-of-the-art techniques for reconstructing neural implicit surfaces from multi-view images or point clouds. Quantitative and qualitative evaluations show that, compared with existing sampling and optimization methods, our approach allows faster convergence, better generalization, and accurate recovery of details and topology.