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
- pp 11108-11117
TLDR
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.Abstract:
We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200x faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.read more
Citations
More filters
Journal ArticleDOI
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.
Book ChapterDOI
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
TL;DR: In this paper, the authors propose Sparse Point-Voxel Convolution (SPVConv), a lightweight 3D module that equips the vanilla Sparse Convolution with the high-resolution point-based branch.
Proceedings ArticleDOI
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
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.
Book ChapterDOI
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
TL;DR: Li et al. as mentioned in this paper proposed Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image, which can be implemented as a series of element-wise multiplications, im2col, and standard convolution.
Proceedings Article
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
TL;DR: 3D-BoNet is a novel, conceptually simple and general framework for instance segmentation on 3D point clouds that surpasses existing work on both ScanNet and S3DIS datasets while being approximately 10x more computationally efficient.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TL;DR: This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Proceedings Article
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu,Jimmy Ba,Ryan Kiros,Kyunghyun Cho,Aaron Courville,Ruslan Salakhudinov,Ruslan Salakhudinov,Rich Zemel,Rich Zemel,Yoshua Bengio,Yoshua Bengio +10 more
TL;DR: An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound.
Posted Content
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu,Jimmy Ba,Ryan Kiros,Kyunghyun Cho,Aaron Courville,Ruslan Salakhutdinov,Richard S. Zemel,Yoshua Bengio +7 more
TL;DR: This paper proposed an attention-based model that automatically learns to describe the content of images by focusing on salient objects while generating corresponding words in the output sequence, which achieved state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.
Proceedings Article
Policy Gradient Methods for Reinforcement Learning with Function Approximation
TL;DR: This paper proves for the first time that a version of policy iteration with arbitrary differentiable function approximation is convergent to a locally optimal policy.