Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

Engelmann, Francis; Kontogianni, Theodora; Schult, Jonas; Leibe, Bastian

doi:10.1007/978-3-030-11015-4_29

Cited by 80 publications

(60 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…mean IoU Overall accuracy(%) PointNet [4] 47.71 78.62 A-SCN [33] 52.72 81.59 SEGCloud [27] 48.92 -G+RCU [8] 49.7 81.1 RSNet [12] 56.47 -Engelmann et al [9] 58 IoU of our model is 56.63% and the overall accuracy is 84.13%. Some of the experimental results are shown in Figure 6.…”

Section: Methodsmentioning

confidence: 81%

Point clouds learning with attention-based graph convolution networks

2020

View full text Add to dashboard Cite

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification techniques such as the convolution neural network to point clouds analysis directly. To solve this problem, we propose a novel network structure, named Attention-based Graph Convolution Networks (AGCN), to extract point clouds features. Taking the learning process as a message propagation between adjacent points, we introduce an attention mechanism to AGCN for analyzing the relationships between local features of the points. In addition, we introduce an additional global graph structure network to compensate for the relative information of the individual points in the graph structure network. The proposed network is also extended to an encoder-decoder structure for segmentation tasks. Experimental results show that the proposed network can achieve state-of-the-art performance in both classification and segmentation tasks.

show abstract

Section: Methodsmentioning

confidence: 81%

Point clouds learning with attention-based graph convolution networks

2020

View full text Add to dashboard Cite

show abstract

“…RS-CNN performed well on ModelNet40 which achieves a state-of-the-art performance as can be seen in table 2. In another work, [97] address the problem of 3D semantic segmentation of unstructured point clouds using a deep learning architecture by introducing grouping techniques that define point neighborhoods in the initial world space and the learned feature space. They use a dedicated loss functions to help structure the learned point feature space by defining the neighborhood in an adaptive manner which is very sensitive to the local geometry by utilizing k-means clustering on the input point cloud and then defining dynamic neighborhoods in the learned feature space using K-nearest neighbor (KNN).…”

Section: ) Performance Of Deep Learning Methods On Point Cloudsmentioning

confidence: 99%

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

et al. 2020

View full text Add to dashboard Cite

Deep learning approach has been used extensively in image analysis tasks. However, implementing the methods in 3D data is a bit complex because most of the previously designed deep learning architectures used 1D or 2D as input. In this work, the performance of deep learning methods on different 3D data representations has been reviewed. Based on the categorization of the different 3D data representations proposed in this paper, the importance of choosing a suitable 3D data representation which depends on simplicity, usability, and efficiency has been highlighted. Furthermore, the origin and contents of the major 3D datasets were discussed in detail. Due to growing interest in 3D object retrieval and classification tasks, the performance of different 3D object retrieval and classification on ModelNet40 dataset were compared. According to the findings in this work, multi views methods surpass voxel-based methods and with increased layers and enough data augmentation the performance can still be increased. Therefore, it can be concluded that deep learning together with a suitable 3D data representation gives an effective approach for improving the performance of 3D shape analysis. Finally, some possible directions for future researches were suggested.

show abstract

“…PointNet [41], along its multiscale variant PointNet++ [41], is one of the most prominent point-based networks. It has been successfully applied in point set segmentation [10,40], generation [1,13,56], consolidation [14,45,58], deformation [57], completion [15,60] and upsampling [58,59,61]. Zhang et al [61] extend a PointNet-based point generation model [1] to point set upsampling.…”

Section: Related Workmentioning

confidence: 99%

Patch-Based Progressive 3D Point Set Upsampling

Wang

Huang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

243

185

View full text Add to dashboard Cite

Figure 1: We develop a deep neural network for 3D point set upsampling. Intuitively, our network learns different levels of detail in multiple steps, where each step focuses on a local patch from the output of the previous step. By progressively training our patch-based network end-to-end, we successfully upsample a sparse set of input points, step by step, to a dense point set with rich geometric details. Here we use circle plates for points rendering, which are color-coded by point normals. AbstractWe present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-theart learning-based [58,59], and optimazation-based [23] approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details. The data and code are at https://github.com/yifita/3pu.

show abstract

Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

Cited by 80 publications

References 28 publications

Point clouds learning with attention-based graph convolution networks

Point clouds learning with attention-based graph convolution networks

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

Patch-Based Progressive 3D Point Set Upsampling

Contact Info

Product

Resources

About