mlsanityData to 7 Oct 2026

Improving Lidar-Based Semantic Segmentation of Top-View Grid Maps by Learning Features in Complementary Representations

arXiv 2203.01151 ↗First posted 2 Mar 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce a novel way to predict semantic information from sparse, single-shot LiDAR measurements in the context of autonomous driving. In particular, we fuse learned features from complementary representations. The approach is aimed specifically at improving the semantic segmentation of top-view grid maps. Towards this goal the 3D LiDAR point cloud is projected onto two orthogonal 2D representations. For each representation a tailored deep learning architecture is developed to effectively extract semantic information which are fused by a superordinate deep neural network. The contribution of this work is threefold: (1) We examine different stages within the segmentation network for fusion. (2) We quantify the impact of embedding different features. (3) We use the findings of this survey to design a tailored deep neural network architecture leveraging respective advantages of different representations. Our method is evaluated using the SemanticKITTI dataset which provides a point-wise semantic annotation of more than 23.000 LiDAR measurements.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 28 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

15 of 28 references.

References · 15

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  9. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  10. 2014Simultaneous Detection and Segmentationcited by 158
  11. 2015Multimodal Deep Learning for Robust RGB-D Object Recognitioncited by 56
  12. 2019Capturing Object Detection Uncertainty in Multi-Layer Grid Mapscited by 10
3 more
  1. 2018Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networkscited by 6
  2. 2020Exploiting Multi-Layer Grid Maps for Surround-View Semantic Segmentation of Sparse LiDAR Datacited by 5
  3. 2017The Stixel world: A medium-level representation of traffic scenescited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoringcited by 2