We propose Neural Gradient Learning (NGL), a deep learning approach to learn
gradient vectors with consistent orientation from 3D point clouds for normal
estimation. It has excellent gradient approximation properties for the
underlying geometry of the data. We utilize a simple neural network to
parameterize the objective function to produce gradients at points using a
global implicit representation. However, the derived gradients usually drift
away from the ground-truth oriented normals due to the lack of local detail
descriptions. Therefore, we introduce Gradient Vector Optimization (GVO) to
learn an angular distance field based on local plane geometry to refine the
coarse gradient vectors. Finally, we formulate our method with a two-phase
pipeline of coarse estimation followed by refinement. Moreover, we integrate
two weighting functions, i.e., anisotropic kernel and inlier score, into the
optimization to improve the robust and detail-preserving performance. Our
method efficiently conducts global gradient approximation while achieving
better accuracy and generalization ability of local feature description. This
leads to a state-of-the-art normal estimator that is robust to noise, outliers
and point density variations. Extensive evaluations show that our method
outperforms previous works in both unoriented and oriented normal estimation on
widely used benchmarks. The source code and pre-trained models are available at
this https URL

我们提出了神经梯度学习（NGL），一种用于从三维点云中学习具有一致方向的梯度向量的深度学习方法，具有出色的梯度近似性能。我们利用简单的神经网络对目标函数进行参数化，使用全局隐式表示在点上产生梯度；然而，由于缺乏局部详细描述，导致得到的梯度通常与真实的定向法线相差很大。因此，我们引入了基于局部平面几何的梯度向量优化（GVO），以学习角距离场以细化粗糙的梯度向量。最后，我们用粗糙估计后的细化进行我们的方法的二阶段流程。此外，我们将两个加权函数（各向异性核和内点得分）整合到优化中，以提高鲁棒性和保持细节的性能。我们的方法在全局梯度近似性能高效且同时具有更好的局部特征描述的准确性和泛化能力，因此成为具有抗噪声、异常值和点密度变化能力的最先进的法线估计器。广泛的评估结果表明，我们的方法在常用基准测试中无定向和定向法线估计方面优于之前的工作。源代码和预训练模型可以在此 https URL 获取。

定向点法线估计的神经梯度学习和优化

Neural Gradient Learning and Optimization for Oriented Point Normal  Estimation

Interest point detection and local feature description are fundamental steps
in many computer vision applications. Classical methods for these tasks are
based on a detect-then-describe paradigm where separate handcrafted methods are
used to first identify repeatable keypoints and then represent them with a
local descriptor. Neural networks trained with metric learning losses have
recently caught up with these techniques, focusing on learning repeatable
saliency maps for keypoint detection and learning descriptors at the detected
keypoint locations. In this work, we argue that salient regions are not
necessarily discriminative, and therefore can harm the performance of the
description. Furthermore, we claim that descriptors should be learned only in
regions for which matching can be performed with high confidence. We thus
propose to jointly learn keypoint detection and description together with a
predictor of the local descriptor discriminativeness. This allows us to avoid
ambiguous areas and leads to reliable keypoint detections and descriptions. Our
detection-and-description approach, trained with self-supervision, can
simultaneously output sparse, repeatable and reliable keypoints that
outperforms state-of-the-art detectors and descriptors on the HPatches dataset.
It also establishes a record on the recently released Aachen Day-Night
localization dataset.

本论文提出了一种同时学习关键点检测、特征描述和本地描述符可区分性预测器的方法，用于解决经典方法中存在的重复区域不具有判别力和描述符在存在歧义区域中的性能问题，在 HPatches 和 Aachen Day-Night 数据集上性能均表现优异。