论文标题
点云通过梯度领域的动量上升
Point Cloud Denoising via Momentum Ascent in Gradient Fields
论文作者
论文摘要
为了实现点云降级，传统方法在很大程度上依赖几何先验，而大多数基于学习的方法都遭受异常值和细节的损失。最近，提出了基于梯度的方法，以使用神经网络从嘈杂的点云中估算梯度场，并根据估计的梯度来完善每个点的位置。但是，预测的梯度可能会波动，导致扰动和不稳定的解决方案，以及长时间的推理时间。为了解决这些问题，我们开发了在确定点轨迹时利用先前迭代的信息的动量梯度上升方法，从而提高了解决方案的稳定性并减少推理时间。实验表明，所提出的方法的表现优于最先进的方法，这些方法具有各种点云，噪声类型和噪声水平。代码可用：https：//github.com/indigopurple/mag
To achieve point cloud denoising, traditional methods heavily rely on geometric priors, and most learning-based approaches suffer from outliers and loss of details. Recently, the gradient-based method was proposed to estimate the gradient fields from the noisy point clouds using neural networks, and refine the position of each point according to the estimated gradient. However, the predicted gradient could fluctuate, leading to perturbed and unstable solutions, as well as a long inference time. To address these issues, we develop the momentum gradient ascent method that leverages the information of previous iterations in determining the trajectories of the points, thus improving the stability of the solution and reducing the inference time. Experiments demonstrate that the proposed method outperforms state-of-the-art approaches with a variety of point clouds, noise types, and noise levels. Code is available at: https://github.com/IndigoPurple/MAG
