mlsanityData to 14 Oct 2026

DRINet++: Efficient Voxel-as-point Point Cloud Segmentation

arXiv 2111.08318 ↗First posted 16 Nov 2021cs.CV cs.ROcited by 23

Not on the map. Why?

Abstract (arXiv)

Recently, many approaches have been proposed through single or multiple representations to improve the performance of point cloud semantic segmentation. However, these works do not maintain a good balance among performance, efficiency, and memory consumption. To address these issues, we propose DRINet++ that extends DRINet by enhancing the sparsity and geometric properties of a point cloud with a voxel-as-point principle. To improve efficiency and performance, DRINet++ mainly consists of two modules: Sparse Feature Encoder and Sparse Geometry Feature Enhancement. The Sparse Feature Encoder extracts the local context information for each point, and the Sparse Geometry Feature Enhancement enhances the geometric properties of a sparse point cloud via multi-scale sparse projection and attentive multi-scale fusion. In addition, we propose deep sparse supervision in the training phase to help convergence and alleviate the memory consumption problem. Our DRINet++ achieves state-of-the-art outdoor point cloud segmentation on both SemanticKITTI and Nuscenes datasets while running significantly faster and consuming less memory.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 47 of its 61 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

47 of 61 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2016Pyramid Scene Parsing Networkcited by 2,479
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
35 more
  1. 2020Point Transformercited by 1,470
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  7. 2020PCT: Point cloud transformercited by 732
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  10. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  11. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  12. 2019Selective Kernel Networkscited by 403
  13. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  14. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  15. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  16. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  17. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  18. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  19. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  20. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  21. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  22. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  23. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  24. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  25. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  26. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  27. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  28. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  29. 2019JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldscited by 62
  30. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  31. 2019LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Latticescited by 38
  32. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  33. 2021LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignmentcited by 26
  34. 2021DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentationcited by 22
  35. 2019LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networkscited by 14

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 9; 2024: 5; 2025: 6.

23 papers.

Sort:

By area:

  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  2. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  3. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  4. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 233
  5. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  6. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 86
  7. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  8. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 52
  9. 2022GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentationcited by 36
  10. 2024OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Predictioncited by 32
  11. 2025Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Drivingcited by 29
  12. 2025QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Predictioncited by 20
11 more
  1. 2024InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Predictioncited by 14
  2. 2023Regulating Intermediate 3D Features for Vision-Centric Autonomous Drivingcited by 12
  3. 2023LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perceptioncited by 11
  4. 2024GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splattingcited by 6
  5. 2023OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarioscited by 2
  6. 2023SOccDPT: Semi-Supervised 3D Semantic Occupancy from Dense Prediction Transformers trained under memory constraintscited by 2
  7. 2025Point Cloud Based Scene Segmentation: A Surveycited by 2
  8. 2025SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representationcited by 1
  9. 2024Efficiently Expanding Receptive Fields: Local Split Attention and Parallel Aggregation for Enhanced Large-scale Point Cloud Semantic Segmentationcited by 0
  10. 2025GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Predictioncited by 0
  11. 2025HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Predictioncited by 0