PointGMM: A Neural GMM Network for Point Clouds

Hertz, Amir; Hanocka, Rana; Giryes, Raja; Cohen–Or, Daniel

doi:10.1109/cvpr42600.2020.01207

Cited by 59 publications

(36 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yan et al [27] proposed PointASNL to deal with noise in point cloud processing, using a self-attention mechanism to update features for local groups of points. Hertz et al [28] proposed PointGMM for shape interpolation with both multilayer perceptron (MLP) splits and attentional splits.…”

Section: Point-based Deep Learningmentioning

confidence: 99%

PCT: Point cloud transformer

et al. 2021

View full text Add to dashboard Cite

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer (PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

show abstract

Section: Point-based Deep Learningmentioning

confidence: 99%

PCT: Point cloud transformer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, self-attention mechanism and Transformer has been employed in point cloud processing, including PointASNL [Yan et al 2020], PointGMM [Hertz et al 2020], PCT ], Point Transformer [Zhao et al 2020]. We borrow from both 3D point feature learning and Transformer.…”

Section: Point Set Learningmentioning

confidence: 99%

TreePartNet

et al. 2021

View full text Add to dashboard Cite

We present TreePartNet , a neural network aimed at reconstructing tree geometry from point clouds obtained by scanning real trees. Our key idea is to learn a natural neural decomposition exploiting the assumption that a tree comprises locally cylindrical shapes. In particular, reconstruction is a two-step process. First, two networks are used to detect priors from the point clouds. One detects semantic branching points, and the other network is trained to learn a cylindrical representation of the branches. In the second step, we apply a neural merging module to reduce the cylindrical representation to a final set of generalized cylinders combined by branches. We demonstrate results of reconstructing realistic tree geometry for a variety of input models and with varying input point quality, e.g., noise, outliers, and incompleteness. We evaluate our approach extensively by using data from both synthetic and real trees and comparing it with alternative methods.

show abstract

“…The pre-processed data are then used to train three different generative networks: PointGrow (Sun, Wang, Liu, Siegel, & Sarma, 2020), PointFlow (Yang et al, 2019), and PointGMM (Hertz, Hanocka, Giryes, & Cohen-Or, 2020).…”

Section: Generative Approaches For Point Cloud Generationmentioning

confidence: 99%

“…In this context, the aim of this paper is to propose a framework based on DL that synthetically generates additional architectural elements to increase segmentation accuracy. To generate novel scenes, we use three different generative networks: PointGrow (Sun, Wang, Liu, Siegel, & Sarma, 2020), PointFlow (Yang et al, 2019, and PointGMM (Hertz, Hanocka, Giryes, & Cohen-Or, 2020). Moreover, to compare the best performances we train a novel Deep Neural Network, namely DGCNN-Mod that classifies the synthetically generate scenes (Pierdicca et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generative Networks for Point Cloud Generation in Cultural Heritage Domain

Martini

Pierdicca

Paolanti

et al. 2021

Proceedings ARQUEOLÓGICA 2.0 - 9th International Congress &Amp; 3rd GEORES - GEOmatics and pREServation

View full text Add to dashboard Cite

In the Cultural Heritage (CH) domain, the semantic segmentation of 3D point clouds with Deep Learning (DL) techniques allows to recognize historical architectural elements, at a suitable level of detail, and hence expedite the process of modelling historical buildings for the development of BIM models from survey data. However, it is more difficult to collect a balanced dataset of labelled architectural elements for training a network. In fact, the CH objects are unique, and it is challenging for the network to recognize this kind of data. In recent years, Generative Networks have proven to be proper for generating new data. Starting from such premises, in this paper Generative Networks have been used for augmenting a CH dataset. In particular, the performances of three state-of-art Generative Networks such as PointGrow, PointFLow and PointGMM have been compared in terms of Jensen-Shannon Divergence (JSD), the Minimum Matching Distance-Chamfer Distance (MMD-CD) and the Minimum Matching Distance-Earth Mover’s Distance (MMD-EMD). The objects generated have been used for augmenting two classes of ArCH dataset, which are columns and windows. Then a DGCNN-Mod network was trained and tested for the semantic segmentation task, comparing the performance in the case of the ArCH dataset without and with augmentation.

show abstract

PointGMM: A Neural GMM Network for Point Clouds

Cited by 59 publications

References 25 publications

PCT: Point cloud transformer

PCT: Point cloud transformer

TreePartNet

Generative Networks for Point Cloud Generation in Cultural Heritage Domain

Contact Info

Product

Resources

About