# M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation

arXiv: https://arxiv.org/abs/2204.05088 · HTML: https://mlsanity.com/paper/2204.05088/

## Key facts

- Cited by 156 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 44 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again](https://mlsanity.com/paper/1711.10006/) (2017)
- [Efficiently Identifying Task Groupings for Multi-Task Learning](https://mlsanity.com/paper/2109.04617/) (2021)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)
- [Cross-view Semantic Segmentation for Sensing Surroundings](https://mlsanity.com/paper/1906.03560/) (2019)

## Built on by (most cited first, 30 of 156)

- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?](https://mlsanity.com/paper/2312.03031/) (2023)
- [Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving](https://mlsanity.com/paper/2305.06242/) (2023)
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://mlsanity.com/paper/2307.01492/) (2023)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://mlsanity.com/paper/2206.15398/) (2022)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [PlanT: Explainable Planning Transformers via Object-Level Representations](https://mlsanity.com/paper/2210.14222/) (2022)
- [FB-BEV: BEV Representation from Forward-Backward View Transformations](https://mlsanity.com/paper/2308.02236/) (2023)
- [BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo](https://mlsanity.com/paper/2209.10248/) (2022)
- [EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation](https://mlsanity.com/paper/2303.12787/) (2023)
- [SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving](https://mlsanity.com/paper/2306.09001/) (2023)
- [UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation](https://mlsanity.com/paper/2308.07732/) (2023)
- [HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer](https://mlsanity.com/paper/2304.10628/) (2023)
- [Far3D: Expanding the Horizon for Surround-view 3D Object Detection](https://mlsanity.com/paper/2308.09616/) (2023)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception](https://mlsanity.com/paper/2303.05970/) (2023)
- [LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusion](https://mlsanity.com/paper/2307.00724/) (2023)
- [Graph-based Topology Reasoning for Driving Scenes](https://mlsanity.com/paper/2304.05277/) (2023)
- [FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View](https://mlsanity.com/paper/2403.02710/) (2024)
- [Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2205.14951/) (2022)
- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection](https://mlsanity.com/paper/2208.12079/) (2022)

## Abstract (arXiv)

In this paper, we propose M2BEV, a unified framework that jointly performs 3D object detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera image inputs. Unlike the majority of previous works which separately process detection and segmentation, M2BEV infers both tasks with a unified model and improves efficiency. M2BEV efficiently transforms multi-view 2D image features into the 3D BEV feature in ego-car coordinates. Such BEV representation is important as it enables different tasks to share a single encoder. Our framework further contains four important designs that benefit both accuracy and efficiency: (1) An efficient BEV encoder design that reduces the spatial dimension of a voxel feature map. (2) A dynamic box assignment strategy that uses learning-to-match to assign ground-truth 3D boxes with anchors. (3) A BEV centerness re-weighting that reinforces with larger weights for more distant predictions, and (4) Large-scale 2D detection pre-training and auxiliary supervision. We show that these designs significantly benefit the ill-posed camera-based 3D perception tasks where depth information is missing. M2BEV is memory efficient, allowing significantly higher resolution images as input, with faster inference speed. Experiments on nuScenes show that M2BEV achieves state-of-the-art results in both 3D object detection and BEV segmentation, with the best single model achieving 42.5 mAP and 57.0 mIoU in these two tasks, respectively.