Open AccessPosted Content
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
TL;DR: RS-CNN as mentioned in this paper extends regular grid CNN to irregular configuration for point cloud analysis, where the convolutional weight for local point set is forced to learn a highlevel relation expression from predefined geometric priors, between a sampled point from this point set and the others.
read more
Abstract: Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an inductive local representation with explicit reasoning about the spatial layout of points can be obtained, which leads to much shape awareness and robustness. With this convolution as a basic operator, RS-CNN, a hierarchical architecture can be developed to achieve contextual shape-aware learning for point cloud analysis. Extensive experiments on challenging benchmarks across three tasks verify RS-CNN achieves the state of the arts.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Qingyong Hu,Bo Yang,Linhai Xie,Stefano Rosa,Yulan Guo,Zhihua Wang,Niki Trigoni,Andrew Markham +7 more
- 14 Jun 2020
TL;DR: This paper introduces RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds, and introduces a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details.
Deep Learning for 3D Point Clouds: A Survey
TL;DR: This paper presents a comprehensive review of recent progress in deep learning methods for point clouds, covering three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation.
PCT: Point cloud transformer
TL;DR: A novel framework based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing, is presented, which is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
Mutian Xu,Runyu Ding,Hengshuang Zhao,Xiaojuan Qi +3 more
- 01 Jun 2021
TL;DR: PAConv as mentioned in this paper constructs the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weights are self-adaptively learned from point positions through ScoreNet.
PF-Net: Point Fractal Network for 3D Point Cloud Completion
Zitian Huang,Yikuan Yu,Jiawen Xu,Feng Ni,Xinyi Le +4 more
- 14 Jun 2020
TL;DR: In this article, a Point Fractal Network (PF-Net) is proposed to estimate the missing point cloud hierarchically by utilizing a feature-points-based multi-scale generating network.
References
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
•Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
•Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
- 06 Jul 2015
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.