Neural Fields as Learnable Kernels for 3D Reconstruction
Neural Fields as Learnable Kernels for 3D Reconstruction
复制标题
DOI：
10.1109/cvpr52688.2022.01795
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Francis Williams;Zan Gojcic;S. Khamis;D. Zorin;Joan Bruna;S. Fidler;O. Litany
中科院分区：
文献类型：
--
作者：
Francis Williams;Zan Gojcic;S. Khamis;D. Zorin;Joan Bruna;S. Fidler;O. Litany
我们提出了神经核场：一种基于学习核岭回归重建隐式3D形状的新方法。我们的技术在从稀疏定向点重建3D对象和大型场景时达到了最先进的结果，并且可以在训练集之外重建形状类别，几乎没有准确性下降。我们的方法的核心见解是，当所选择的内核具有适当的归纳偏差时，内核方法对于重建形状是非常有效的。因此，我们将形状重建问题分解为两个部分：（1）从数据中学习核参数的骨干神经网络，以及（2）通过使用学习的核求解简单的正定线性系统来实时拟合输入点的核岭回归。由于这种因式分解，我们的重建在稀疏点密度下获得了数据驱动方法的好处，同时保持插值行为，随着输入采样密度的增加，插值行为收敛到地面真实形状。我们的实验表明，一个强大的泛化能力，对象以外的训练集类别和扫描的场景。源代码和预训练模型可在https://nv-tlabs.github.io/nkf上获得。
We present Neural Kernel Fields: a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression. Our technique achieves state-of-the-art results when reconstructing 3D objects and large scenes from sparse oriented points, and can reconstruct shape categories outside the training set with almost no drop in accuracy. The core insight of our approach is that kernel methods are extremely effective for reconstructing shapes when the chosen kernel has an appropriate inductive bias. We thus factor the problem of shape reconstruction into two parts: (1) a backbone neural network which learns kernel parameters from data, and (2) a kernel ridge regression that fits the input points on-the-fly by solving a simple positive definite linear system using the learned kernel. As a result of this factorization, our reconstruction gains the benefits of data-driven methods under sparse point density while maintaining interpolatory behavior, which converges to the ground truth shape as input sampling density increases. Our experiments demonstrate a strong generalization capability to objects outside the train-set category and scanned scenes. Source code and pretrained models are available at https://nv-tlabs.github.io/nkf.