Unstructured Point Cloud Semantic Labeling Using Deep Segmentation Networks

By Alexandre Boulch, Bertrand Le Saux, Nicolas Audebert. 3DOR@Eurographics, 2017

329 citations recorded by the source corpus.

Subfields: Computational Mechanics, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/6d9756a6762d52142a22bfaef0382aeb05b72587

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Environmental Engineering

In Geology

Citations in the corpus

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (2017, background): “Applications of learning on point clouds include shape completion and recognition [57], unmanned autonomous vehicles [36], 3D object detection, recognition and classification [9, 33, 40, 41, 48, 49, 53], contour detection [21], layout inference [18], scene labeling [31], category discovery [60], poi”
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds (2017, background): “Applications of learning on point clouds include shape completion and recognition [54], unmanned autonomous vehicles [34], 3D object detection, recognition and classification [9, 31, 38, 39, 45, 46, 50], contour detection [20], layout inference [16], scene labeling [29], category discovery [57], poi”
Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds (2017, background): “In [2], the authors are performing 2D convolutions in 2D snapshots of a 3D point cloud and then project the labels back to 3D space.”
Tangent Convolutions for Dense Prediction in 3D (2018, methodology): “[5] train a ConvNet on images rendered from point clouds using randomly placed virtual cameras.”
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (2021, methodology): “Notably, (Boulch et al., 2017) use point cloud density to create scene meshes, which are then put into a mesh renderer to generate many image views at different scales.”
KPConv: Flexible and Deformable Convolution for Point Clouds (2019, background): “Image-based networks are often multi-view, using a set of 2D images rendered from the point cloud at different viewpoints [34, 4, 17].”
DeepGCNs: Can GCNs Go As Deep As CNNs? (2019, background): “Several attempts in creating structure from 3D data exist by either representing it with multiple 2D views [35, 9, 3, 22], or by voxelization [5, 28, 32, 37].”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, methodology): “Our method outperforms [6] by 2.2 mIOU points and 2.28% accuracy and sets a new state-of-the-art on that challenge.”
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion (2020, background): “Previous works projected all points scanned by the rotating LiDAR onto 2D images by plane projection (Lawin et al. 2017; Boulch, Le Saux, and Audebert 2017; Tatarchenko et al. 2018) or spherical projection (Wu et al. 2018, 2019).”
ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics (2019, unknown): “5 SnapNet [5] 59.”
An End-to-End Transformer Model for 3D Object Detection (2021, methodology): “Projection methods [3, 19, 25, 26, 59, 60, 65] project 3D data into 2D planes and convert it into 2D grids.”
Multisource and Multitemporal Data Fusion in Remote Sensing: A Comprehensive Review of the State of the Art (2019, methodology): “Generally, the majority of published approaches for multisource point cloud classification that resulted in a classified point cloud worked in the image domain and then transferred the classification results back to the point cloud [115].”
Deep Learning for 3D Point Clouds: A Survey (2019, methodology): “(a) and (b) are originally shown in [182] and [183], respectively.”
Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs (2017, methodology): “This can be explained by the ability of the partitioning algorithm to detect artifacts due to their singular shape, while they are hard to capture using snapshots, as suggested by [5].”
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (2019, background): “For fair comparison, we only include the results of recently published strong baselines [4, 52, 53, 46, 69, 56, 26] and the current state-of-the-art approach KPConv [54].”
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds (2021, background): “Since point cloud data has irregular structure in 3D space, early works [44, 21, 6] project point clouds to multiview images and then utilize conventional convolutions for feature learning.”
SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks (2017, methodology): “We show that this SnapNet framework, which extends our work presented in [11], can be applied to various scenes, outdoor and indoor, and for classes which may highly differ depending on the application.”