mlsanityData to 7 Oct 2026

DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds

arXiv 2106.00376 ↗First posted 1 Jun 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation of building facade is significant in various applications, such as urban building reconstruction and damage assessment. As there is a lack of 3D point clouds datasets related to the fine-grained building facade, we construct the first large-scale building facade point clouds benchmark dataset for semantic segmentation. The existing methods of semantic segmentation cannot fully mine the local neighborhood information of point clouds. Addressing this problem, we propose a learnable attention module that learns Dual Local Attention features, called DLA in this paper. The proposed DLA module consists of two blocks, including the self-attention block and attentive pooling block, which both embed an enhanced position encoding block. The DLA module could be easily embedded into various network architectures for point cloud segmentation, naturally resulting in a new 3D semantic segmentation network with an encoder-decoder architecture, called DLA-Net in this work. Extensive experimental results on our constructed building facade dataset demonstrate that the proposed DLA-Net achieves better performance than the state-of-the-art methods for semantic segmentation.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 62 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

34 of 62 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2020PCT: Point cloud transformercited by 730
  10. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  11. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  12. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
22 more
  1. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  2. 2020Exploring Self-attention for Image Recognitioncited by 313
  3. 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
  4. 2019Local Relation Networks for Image Recognitioncited by 210
  5. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  6. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  7. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  8. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  9. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  10. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  11. 2017Deep Projective 3D Semantic Segmentationcited by 81
  12. 2017Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classificationcited by 65
  13. 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
  14. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  15. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  16. 2018Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstructioncited by 44
  17. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  18. 2019Point Attention Network for Semantic Segmentation of 3D Point Cloudscited by 29
  19. 2020Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenescited by 26
  20. 2016Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networkscited by 25
  21. 2019Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modelingcited by 25
  22. 2019Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representationscited by 10

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 2.

7 papers.

  1. 2025Texture2LoD3: Enabling LoD3 Building Reconstruction With Panoramic Imagescited by 7
  2. 2023Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentationcited by 6
  3. 2024Deep Learning on 3D Semantic Segmentation: A Detailed Reviewcited by 6
  4. 2022LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLADcited by 5
  5. 2022Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Cloudscited by 4
  6. 2024Enriching thermal point clouds of buildings using semantic 3D building modelscited by 1
  7. 2025Adaptive Detection of Fast Moving Celestial Objects Using a Mixture of Experts and Physical-Inspired Neural Networkcited by 0