论文标题
点云降解的可区分流形重构
Differentiable Manifold Reconstruction for Point Cloud Denoising
论文作者
论文摘要
3D点云通常由于采集设备的固有限制而受到噪声的扰动，这阻塞了下游任务，例如表面重建，渲染等。先前的作品主要推断噪声点从基础表面的位移，但是未被指定以明确恢复表面，并可能导致优化的脱糖性结果。为此，我们建议从不同的噪声扰动及其嵌入式邻域功能中学习嘈杂点云的基本歧管，旨在捕获点云中的内在结构。具体来说，我们提出了一个类似自动编码器的神经网络。编码器学习每个点的局部和非本地特征表示形式，然后通过自适应可区分的池操作以低噪声点样品。之后，解码器通过将每个采样点以及其邻域的嵌入特征转换为围绕该点的局部表面，从而渗透了基础歧管。通过在重建的歧管上重新采样，我们获得了一个DeNoist的点云。此外，我们设计了无监督的培训损失，以便可以以无监督或监督的方式对我们的网络进行培训。实验表明，在合成噪声和现实世界噪声下，我们的方法显着优于最先进的denoising方法。代码和数据可在https://github.com/luost26/dmrdenoise上找到
3D point clouds are often perturbed by noise due to the inherent limitation of acquisition equipments, which obstructs downstream tasks such as surface reconstruction, rendering and so on. Previous works mostly infer the displacement of noisy points from the underlying surface, which however are not designated to recover the surface explicitly and may lead to sub-optimal denoising results. To this end, we propose to learn the underlying manifold of a noisy point cloud from differentiably subsampled points with trivial noise perturbation and their embedded neighborhood feature, aiming to capture intrinsic structures in point clouds. Specifically, we present an autoencoder-like neural network. The encoder learns both local and non-local feature representations of each point, and then samples points with low noise via an adaptive differentiable pooling operation. Afterwards, the decoder infers the underlying manifold by transforming each sampled point along with the embedded feature of its neighborhood to a local surface centered around the point. By resampling on the reconstructed manifold, we obtain a denoised point cloud. Further, we design an unsupervised training loss, so that our network can be trained in either an unsupervised or supervised fashion. Experiments show that our method significantly outperforms state-of-the-art denoising methods under both synthetic noise and real world noise. The code and data are available at https://github.com/luost26/DMRDenoise
