mlsanityData to 7 Oct 2026

On Offline Evaluation of 3D Object Detection for Autonomous Driving

arXiv 2308.12779 ↗First posted 24 Aug 2023cs.CV cs.ROcited by 11

On the map: End-to-end autonomous driving → VLMs for autonomous driving

Abstract (arXiv)

Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in VLMs for autonomous driving, one of 9 directions in End-to-end autonomous driving. Builds on 23 of its 34 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

23 of 34 references.

References · 23

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  7. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  8. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  9. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  10. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  11. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 239
  12. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
11 more
  1. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  2. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  3. 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
  4. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  5. 2018On Offline Evaluation of Vision-based Driving Modelscited by 62
  6. 2020Learning to Evaluate Perception Models Using Planner-Centric Metricscited by 49
  7. 2021Can Offline Testing of Deep Neural Networks Replace Their Online Testing?cited by 24
  8. 2021Injecting Planning-Awareness into Prediction and Detection Evaluationcited by 21
  9. 2021Revisiting 3D Object Detection From an Egocentric Perspectivecited by 18
  10. 2021Risk Ranked Recall: Collision Safety Metric for Object Detection Systems in Autonomous Vehiclescited by 10
  11. 2023Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Drivingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 5; 2026: 2.

11 papers.

  1. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  2. 2024Label-Efficient 3D Object Detection For Road-Side Unitscited by 3
  3. 2024VALO: A Versatile Anytime Framework for LiDAR-based Object Detection Deep Neural Networkscited by 3
  4. 2023Diffusion-Based Particle-DETR for BEV Perceptioncited by 2
  5. 2025nuScenes Revisited: Progress and Challenges in Autonomous Drivingcited by 2
  6. 2024Object criticality for safer navigationcited by 1
  7. 2025Scalable Offline Metrics for Autonomous Drivingcited by 0
  8. 2025Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decisioncited by 0
  9. 2025Physically Realistic Sequence-Level Adversarial Clothing for Robust Human-Detection Evasioncited by 0
  10. 2026STELLAR: Scaling 3D Perception Large Models for Autonomous Drivingcited by 0
  11. 2026PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Comprehensive Review of 3D Object Detection in Autonomous Driving: Technological Advances and Future Directions
  2. 2026Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives
  3. 2022Towards Driving-Oriented Metric for Lane Detection Models
  4. 2023Leveraging the Edge and Cloud for V2X-Based Real-Time Object Detection in Autonomous Driving
  5. 2021On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
  6. 2024OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection
  7. 2025Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring
  8. 2022USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving