RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

Hu, Qingyong; Yang, Bo; Xie, Linhai; Rosa, Stefano; Guo, Yulan; Wang, Zhihua; Trigoni, Niki; Markham, Andrew

doi:10.1109/cvpr42600.2020.01112

Cited by 1,428 publications

(1,011 citation statements)

References 40 publications

Supporting

Mentioning

783

Contrasting

Unclassified

Order By: Relevance

“…The proposed Multi-Scale Attentive Aggregation Network (MSAAN) accessed the large-scale point clouds as a single input and predicted a segmentation map that assigns each point to a category. MSAAN was developed on top of the recent RandLA-Net [23]. Several key adjustments are made for improvements.…”

Section: Methodsmentioning

confidence: 99%

“…(3) A Channel Attentive Enhancement (CAE) module was introduced to the local spatial encoding module of RandLA-Net [23] to further increase the representation ability of local features.…”

Section: Our Workmentioning

confidence: 99%

“…PointWeb [22] proposed an Adaptive Feature Adjustment (AFA) module to learn relationships among local neighboring points. RandLA-Net [23] proposed an efficient and lightweight network to process 3D point clouds by applying random down-sampling to boost efficiency and save memory, introducing a local geometric feature extraction module to capture geometric information, and utilizing an attentive pooling module to aggregate local features.…”

Section: Introductionmentioning

confidence: 99%

“…First, the attention mechanism [29,30], which has been shown to be effective for the global balance and consistency of the encoder and decoder features in recent image segmentation [31,32], has not been applied to point cloud segmentation methods. [20], [22][23][24][25] and [28] only apply the traditional skip connection, i.e., a concatenation operation, to combine encoder and decoder, which results in a semantic gap between the feature layers. Second, the multi-scale convolutional features are critical for grasping the entire structure of a point cloud, but most of the recent methods [20][21][22][23][24][25]27,28] only focus on the structures of input format and the encoder but neglect multi-scale information fusion in the decoder.…”

Section: Introductionmentioning

confidence: 99%

“…[20], [22][23][24][25] and [28] only apply the traditional skip connection, i.e., a concatenation operation, to combine encoder and decoder, which results in a semantic gap between the feature layers. Second, the multi-scale convolutional features are critical for grasping the entire structure of a point cloud, but most of the recent methods [20][21][22][23][24][25]27,28] only focus on the structures of input format and the encoder but neglect multi-scale information fusion in the decoder. The accuracy of point cloud segmentation is expected to improve with a careful design of considering the attention modules and the multi-scale information fusion.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

Geng

Lü

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation of LiDAR point clouds has implications in self-driving, robots, and augmented reality, among others. In this paper, we propose a Multi-Scale Attentive Aggregation Network (MSAAN) to achieve the global consistency of point cloud feature representation and super segmentation performance. First, upon a baseline encoder-decoder architecture for point cloud segmentation, namely, RandLA-Net, an attentive skip connection was proposed to replace the commonly used concatenation to balance the encoder and decoder features of the same scales. Second, a channel attentive enhancement module was introduced to the local attention enhancement module to boost the local feature discriminability and aggregate the local channel structure information. Third, we developed a multi-scale feature aggregation method to capture the global structure of a point cloud from both the encoder and the decoder. The experimental results reported that our MSAAN significantly outperformed state-of-the-art methods, i.e., at least 15.3% mIoU improvement for scene-2 of CSPC dataset, 5.2% for scene-5 of CSPC dataset, and 6.6% for Toronto3D dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

“…(3) A Channel Attentive Enhancement (CAE) module was introduced to the local spatial encoding module of RandLA-Net [23] to further increase the representation ability of local features.…”

Section: Our Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

Geng

Lü

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

Semantic Segmentation of Airborne LiDAR Data for the Development of an Urban 3D Model

Ballouch¹,

Hajji²

2021

Building Information Modeling for a Smart and Sustainable Urban Space

View full text Add to dashboard Cite

A simulation‐assisted point cloud segmentation neural network for human–robot interaction applications

Lin,

Zhong,

Gong

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

With the advancement of industrial automation, the frequency of human–robot interaction (HRI) has significantly increased, necessitating a paramount focus on ensuring human safety throughout this process. This paper proposes a simulation‐assisted neural network for point cloud segmentation in HRI, specifically distinguishing humans from various surrounding objects. During HRI, readily accessible prior information, such as the positions of background objects and the robot's posture, can generate a simulated point cloud and assist in point cloud segmentation. The simulation‐assisted neural network utilizes simulated and actual point clouds as dual inputs. A simulation‐assisted edge convolution module in the network facilitates the combination of features from the actual and simulated point clouds, updating the features of the actual point cloud to incorporate simulation information. Experiments of point cloud segmentation in industrial environments verify the efficacy of the proposed method.

show abstract

RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

Cited by 1,428 publications

References 40 publications

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

Semantic Segmentation of Airborne LiDAR Data for the Development of an Urban 3D Model

A simulation‐assisted point cloud segmentation neural network for human–robot interaction applications

Contact Info

Product

Resources

About