mlsanityData to 7 Oct 2026

On the Robustness of 3D Object Detectors

arXiv 2207.10205 ↗First posted 20 Jul 2022cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to sensor inaccuracies as well as information loss during pre-processing. Thus, it is crucial to design techniques that are robust against these variations. This requires a detailed analysis and understanding of the effect of such variations. This work aims to analyze and benchmark popular point-based 3D object detectors against several data corruptions. To the best of our knowledge, we are the first to investigate the robustness of point-based 3D object detectors. To this end, we design and evaluate corruptions that involve data addition, reduction, and alteration. We further study the robustness of different modules against local and global variations. Our experimental results reveal several intriguing findings. For instance, we show that methods that integrate Transformers at a patch or object level lead to increased robustness, compared to using Transformers at the point level.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 26 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

22 of 26 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
10 more
  1. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  2. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  3. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  4. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  5. 2021Group-Free 3D Object Detection via Transformerscited by 215
  6. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  7. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  8. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  9. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  10. 2021Robustness of Object Detectors in Degrading Weather Conditionscited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  2. 2023Three Pillars improving Vision Foundation Model Distillation for Lidarcited by 43
  3. 2023Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Drivingcited by 37
  4. 2024A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimationcited by 2
  5. 2026SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detectioncited by 0