Pointwise Convolutional Neural Networks

By Binh-Son Hua, Minh-Khoi Tran, Sai-Kit Yeung. 2017

587 citations recorded by the source corpus.

Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored. In this paper, we present a convolutional neural network for semantic segmentation and object recognition with 3D point clouds. At the core of our network is point-wise convolution, a new convolution operator that can be applied at each point of a point cloud. Our fully convolutional network design, while being surprisingly simple to implement, can yield competitive accuracy in both semantic segmentation and object recognition task.

Subfields: Aerospace Engineering, Computational Mechanics, Geology

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Geology

Citations in the corpus

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data (2019, neutral): “, [32, 25, 20, 42, 44, 18, 2, 24, 33, 11] or from autoencoders [45].”
PointConv: Deep Convolutional Networks on 3D Point Clouds (2018, background): “Some latest work [30, 26, 28, 35, 37, 13, 9, 39] directly take raw point clouds as input without converting them to other formats.”
VMamba: Visual State Space Model (2024, background): “In addition to these efforts, progress has been made to propose more advanced convolution operators [5, 24, 61, 6] or more efficient network architectures [69, 4, 58, 23].”
Review: deep learning on 3D point clouds (2020, methodology): “Pointwise convolution is proposed in [34].”
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding (2020, background): “Second, is the choice of neighborhood aggregation mechanism which could either be hierarchical [48, 33, 82, 16, 35], spatial CNN-like [30, 73, 37, 85, 59], spectral [78, 62, 65] or graph-based [72, 64, 68, 54].”
Self-Supervised Pretraining of 3D Features on any Point-Cloud (2021, methodology): “Point-cloud based models [66, 68] are widely used in classification and segmentation tasks [6, 40, 45, 66, 68, 91, 98, 100, 106, 107], 3D reconstruction [23, 90, 110] and 3D object detection [63, 64, 77, 98, 112, 112, 114].”
SoftGroup for 3D Instance Segmentation on Point Clouds (2022, methodology): “Discrete convolution methods [5,8,13,19,25,34] learn the kernels which are regular grids obtaining from point quantization.”
PU-GAN: A Point Cloud Upsampling Adversarial Network (2019, background): “, PointNet [23], PointNet++ [24], SpiderCNN [35], KCNet [26], SPLATNet [29], PointCNN [20], PointConv [13], PointWeb [44], DGCNN [31], etc.”
Patch-Based Progressive 3D Point Set Upsampling (2018, background): “com) with 3D point sets, however, is challenging since, unlike images, the data is unstructured and irregular [3,17,19,34,55].”
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (2022, background): “Later on, many studies design point-wise MLP [25,26], adaptive weight [27, 28] and pseudo grid [29, 30] based methods to extract local features of point clouds or exploit nonlocal operators [31–33] to learn long distance dependency.”
KPConv: Flexible and Deformable Convolution for Point Clouds (2019, methodology): “SpiderCNN [44] defines its kernel as a family of polynomial functions applied with a different weight for each neighbor.”
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (2019, background): “These modules can be generally categorized as: 1) neighbouring feature pooling [44, 32, 21, 70, 69], 2) graph message passing [57, 48, 55, 56, 5, 22, 34], 3) kernel-based convolution [49, 20, 60, 29, 23, 24, 54, 38], and 4) attentionbased aggregation [61, 68, 66, 42].”
Lagrangian Fluid Simulation with Continuous Convolutions (2020, methodology): “A number of methods transferred the convolution concept to point clouds in the context of semantic classiﬁcation and segmentation of 3D objects (Hua et al., 2018; Atzmon et al., 2018; Hermosilla et al., 2018; Li et al., 2018; Su et al., 2018; Wu et al., 2019; Xu et al., 2018; Lei et al., 2019).”
JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields (2019, methodology): “We also compare our method with other state-ofthe-art deep neural networks including PointNet [32], PointwiseCNN [16], and SEGCloud [40].”
PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling (2020, background): “The underlying reason is that, currently, most appealing methods for feature learning is to query a local group around the each sampled point, and then they construct the graph-based learning [30, 42, 50, 14] or define convolution-like operations [12, 47, 8, 3, 44, 34] (we denote them as Point Local”
PU-Net: Point Cloud Upsampling Network (2018, background): “Subsequently, many other networks were proposed for high-level analysis problems with point clouds [18, 13, 21, 34, 28].”
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds (2019, unknown): “Recent learning based approaches mainly include voxel-based [42; 46; 41; 23; 40; 11; 4] and point-based schemes [37; 19; 14; 16; 45].”