mlsanityData to 7 Oct 2026

MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones

arXiv 2207.12716 ↗First posted 26 Jul 2022cs.CV cs.ROcited by 29

Not on the map. Why?

Abstract (arXiv)

In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022. For multi-view camera-only 3D detection, methods based on bird-eye-view or 3D geometric representations can leverage the stereo cues from overlapped regions between adjacent views and directly perform 3D detection without hand-crafted post-processing. However, it lacks direct semantic supervision for 2D backbones, which can be complemented by pretraining simple monocular-based detectors. Our solution is a multi-view framework for 4D detection following this paradigm. It is built upon a simple monocular detector FCOS3D++, pretrained only with object annotations of Waymo, and converts multi-view features to a 3D grid space to detect 3D objects thereon. A dual-path neck for single-frame understanding and temporal stereo matching is devised to incorporate multi-frame information. Our method finally achieves 49.75% mAPL with a single model and wins 2nd place in the WOD challenge, without any LiDAR-based depth supervision during training. The code will be released at https://github.com/Tai-Wang/Depth-from-Motion.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 12 of its 16 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

12 of 16 references.

References · 12

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2017Deformable Convolutional Networkscited by 1,481
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  9. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  10. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  11. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  12. 2022LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detectioncited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 11; 2024: 7; 2025: 1; 2026: 2.

29 papers.

Sort:

By area:

  1. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  2. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  3. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  4. 2022Vision-Centric BEV Perception: A Surveycited by 126
  5. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  6. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  7. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  8. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  9. 2024FreeVS: Generative View Synthesis on Free Driving Trajectorycited by 52
  10. 2023EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detectioncited by 38
  11. 2023Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Reviewcited by 25
  12. 2022Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detectioncited by 19
17 more
  1. 2023GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understandingcited by 17
  2. 2023DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Trackingcited by 11
  3. 2023OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detectioncited by 10
  4. 20233D Video Object Detection with Learnable Object-Centric Global Optimizationcited by 7
  5. 2023A Vision-Centric Approach for Static Map Element Annotationcited by 7
  6. 2024Improving Distant 3D Object Detection Using 2D Box Supervisioncited by 6
  7. 2023QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contextscited by 5
  8. 2024DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perceptioncited by 5
  9. 2023BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereocited by 4
  10. 2024Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detectioncited by 4
  11. 2022Multi-Camera Calibration Free BEV Representation for 3D Object Detectioncited by 3
  12. 2024CAMAv2: A Vision-Centric Approach for Static Map Element Annotationcited by 3
  13. 2024Roadside Monocular 3D Detection Prompted by 2D Detectioncited by 2
  14. 2026Geometry-Grounded Unified 3D Perception for Autonomous Drivingcited by 2
  15. 2024Unveiling the Black Box: Independent Functional Module Evaluation for Bird's-Eye-View Perception Modelcited by 1
  16. 2025DenseBEV: Transforming BEV Grid Cells into 3D Objectscited by 1
  17. 2026CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Camerascited by 0