mlsanityData to 14 Oct 2026

Rethinking Dimensionality Reduction in Grid-based 3D Object Detection

arXiv 2209.09464 ↗First posted 20 Sep 2022cs.CV cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

Bird's eye view (BEV) is widely adopted by most of the current point cloud detectors due to the applicability of well-explored 2D detection techniques. However, existing methods obtain BEV features by simply collapsing voxel or point features along the height dimension, which causes the heavy loss of 3D spatial information. To alleviate the information loss, we propose a novel point cloud detection network based on a Multi-level feature dimensionality reduction strategy, called MDRNet. In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation. Furthermore, the Multi-level Spatial Residuals (MSR) is proposed to fuse the multi-level spatial information in the BEV feature maps. Extensive experiments on nuScenes show that the proposed method outperforms the state-of-the-art methods. The code will be available upon publication.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 20 Sep 2022.

Builds on

27 of 33 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  8. 2019Objects as Pointscited by 1,175
  9. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  12. 2020Tracking Objects as Pointscited by 483
15 more
  1. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  2. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  3. 2017Deep Layer Aggregationcited by 436
  4. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  5. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  6. 2021Voxel Transformer for 3D Object Detectioncited by 247
  7. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  8. 2021Multimodal Virtual Point 3D Detectioncited by 166
  9. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  10. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  11. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  12. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  13. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  14. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  15. 2020InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modelingcited by 35

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 1.

6 papers.

  1. 2023LinK: Linear Kernel for LiDAR-based 3D Perceptioncited by 26
  2. 2023LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perceptioncited by 11
  3. 2023Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformerscited by 8
  4. 2023Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detectioncited by 7
  5. 2023DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detectioncited by 2
  6. 2024Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detectioncited by 0