mlsanityData to 14 Oct 2026

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

arXiv 2303.17597 ↗First posted 30 Mar 2023cs.CV cs.ROcited by 129

Not on the map. Why?

Abstract (arXiv)

The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets often contain data that are meticulously cleaned. Such configurations, however, cannot reflect the reliability of perception models during the deployment stage. In this work, we present Robo3D, the first comprehensive benchmark heading toward probing the robustness of 3D detectors and segmentors under out-of-distribution scenarios against natural corruptions that occur in real-world environments. Specifically, we consider eight corruption types stemming from severe weather conditions, external disturbances, and internal sensor failure. We uncover that, although promising results have been progressively achieved on standard benchmarks, state-of-the-art 3D perception models are at risk of being vulnerable to corruptions. We draw key observations on the use of data representations, augmentation schemes, and training strategies, that could severely affect the model's performance. To pursue better robustness, we propose a density-insensitive training framework along with a simple flexible voxelization strategy to enhance the model resiliency. We hope our benchmark and approach could inspire future research in designing more robust and reliable 3D perception models. Our robustness benchmark suite is publicly available.

Key facts. Cited by 129 papers in the map (data through 14 Oct 2026). Builds on 74 of its 96 references that are in the map. First posted on arXiv 30 Mar 2023.

Builds on

74 of 96 references.

References · 74

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  10. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  11. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  12. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
38 more
  1. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  2. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  3. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  4. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  5. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  6. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 368
  7. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  8. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  9. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  10. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  11. 2021Voxel Transformer for 3D Object Detectioncited by 247
  12. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  13. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  14. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  15. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  16. 2022MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretrainingcited by 187
  17. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  18. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 166
  19. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  20. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  21. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  22. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  23. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 128
  24. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  25. 20223D Common Corruptions and Data Augmentationcited by 119
  26. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 114
  27. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  28. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  29. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  30. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  31. 2021Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weathercited by 97
  32. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 93
  33. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  34. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 80
  35. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
  36. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  37. 2022Multi-modal Sensor Fusion for Auto Driving Perception: A Surveycited by 76
  38. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 19; 2024: 34; 2025: 47; 2026: 29.

129 papers.

Sort:

By area:

  1. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 190
  2. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  3. 2023Drive Like a Human: Rethinking Autonomous Driving with Large Language Modelscited by 160
  4. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 125
  5. 2025Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectivescited by 122
  6. 2024SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Groundingcited by 67
  7. 20253D and 4D World Modeling: A Surveycited by 67
  8. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 66
  9. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  10. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  11. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 54
  12. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
38 more
  1. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 49
  2. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  3. 2023Three Pillars improving Vision Foundation Model Distillation for Lidarcited by 44
  4. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  5. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 41
  6. 2024A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspectivecited by 37
  7. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 33
  8. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 33
  9. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  10. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  11. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  12. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 27
  13. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 26
  14. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 25
  15. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  16. 2024LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusionscited by 18
  17. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 18
  18. 2025Perspective-Invariant 3D Object Detectioncited by 18
  19. 2024MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detectioncited by 17
  20. 2025LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequencescited by 17
  21. 2025MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perceptioncited by 15
  22. 2023CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perceptioncited by 14
  23. 2024Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 14
  24. 2025Resilient Sensor Fusion under Adverse Sensor Failures via Multi-Modal Expert Fusioncited by 14
  25. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 14
  26. 2025SafeMap: Robust HD Map Construction from Incomplete Observationscited by 14
  27. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  28. 2024DSRC: Learning Density-insensitive and Semantic-aware Collaborative Representation against Corruptionscited by 13
  29. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  30. 2024GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precisioncited by 12
  31. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 12
  32. 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusioncited by 12
  33. 20253EED: Ground Everything Everywhere in 3Dcited by 12
  34. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  35. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 10
  36. 2025La La LiDAR: Large-Scale Layout Generation from LiDAR Datacited by 10
  37. 2024Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusioncited by 9
  38. 2025What Really Matters for Robust Multi-Sensor HD Map Construction?cited by 9

50 most cited of 129 All 129 (JSON)