当前位置: X-MOL 学术IEEE Trans. Vis. Comput. Graph. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling
IEEE Transactions on Visualization and Computer Graphics ( IF 4.7 ) Pub Date : 2020-09-28 , DOI: 10.1109/tvcg.2020.3027069
Dongbo Zhang , Xuequan Lu , Hong Qin , Ying He

Point cloud filtering is a fundamental problem in geometry modeling and processing. Despite of significant advancement in recent years, the existing methods still suffer from two issues: 1) they are either designed without preserving sharp features or less robust in feature preservation; and 2) they usually have many parameters and require tedious parameter tuning. In this article, we propose a novel deep learning approach that automatically and robustly filters point clouds by removing noise and preserving their sharp features. Our point-wise learning architecture consists of an encoder and a decoder. The encoder directly takes points (a point and its neighbors) as input, and learns a latent representation vector which goes through the decoder to relate the ground-truth position with a displacement vector. The trained neural network can automatically generate a set of clean points from a noisy input. Extensive experiments show that our approach outperforms the state-of-the-art deep learning techniques in terms of both visual quality and quantitative error metrics. The source code and dataset can be found at https://github.com/dongbo-BUAA-VR/Pointfilter .

中文翻译:

Pointfilter:通过编码器-解码器建模进行点云过滤

点云过滤是几何建模和处理中的一个基本问题。尽管近年来取得了长足的进步,但是现有方法仍然存在两个问题:1)要么在设计时不保留尖锐的特征,要么在保留特征方面不那么健壮。2)它们通常具有许多参数,并且需要繁琐的参数调整。在本文中,我们提出了一种新颖的深度学习方法,该方法可以通过去除噪声并保留其鲜明特征来自动,稳健地过滤点云。我们的逐点学习架构由编码器和解码器组成。编码器直接将点(一个点及其相邻点)作为输入,并学习一个潜在的表示向量,该向量通过解码器将真实位置与位移向量相关联。训练有素的神经网络可以从嘈杂的输入中自动生成一组清洁点。大量实验表明,我们的方法在视觉质量和定量误差指标方面都优于最新的深度学习技术。源代码和数据集可以在以下位置找到https://github.com/dongbo-BUAA-VR/Pointfilter
更新日期:2020-09-28
down
wechat
bug