mlsanityData to 7 Oct 2026

LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation

arXiv 2304.01519 ↗First posted 4 Apr 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors. However, little research has been done to investigate how to incorporate additional supervision on the BEV features to improve proposal generation in the detector head, while still balancing the number of powerful 3D layers and efficient 2D network operations. This paper proposes a novel scene representation that encodes both the semantics and geometry of the 3D environment in 2D, which serves as a dense supervision signal for better BEV feature learning. The key idea is to use auxiliary networks to predict a combination of explicit and implicit semantic probabilities by exploiting their complementary properties. Extensive experiments show that our simple yet effective design can be easily integrated into most state-of-the-art 3D object detectors and consistently improves upon baseline models.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 45 of its 50 references that are in the map. First posted on arXiv 4 Apr 2023.

Builds on

45 of 50 references.

References · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
33 more
  1. 2017Focal Loss for Dense Object Detectioncited by 749
  2. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  6. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  7. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  8. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  9. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  10. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  11. 2021Voxel Transformer for 3D Object Detectioncited by 247
  12. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  13. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  14. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  15. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  16. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  17. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  18. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  19. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  20. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  21. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  22. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  23. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  24. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  25. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  26. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  27. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  28. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  29. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  30. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  31. 2022SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detectioncited by 52
  32. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  33. 2020RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representationcited by 37

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  2. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2