# Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection

arXiv: https://arxiv.org/abs/2204.11582 · HTML: https://mlsanity.com/paper/2204.11582/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 63 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (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)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Rethinking Graph Transformers with Spectral Attention](https://mlsanity.com/paper/2106.03893/) (2021)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [3D Object Detection with Pointformer](https://mlsanity.com/paper/2012.11409/) (2020)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)

## Built on by (most cited first, 30 of 35)

- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection](https://mlsanity.com/paper/2403.16440/) (2024)
- [HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer](https://mlsanity.com/paper/2304.10628/) (2023)
- [Sparse4D v3: Advancing End-to-End 3D Detection and Tracking](https://mlsanity.com/paper/2311.11722/) (2023)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction](https://mlsanity.com/paper/2304.00967/) (2023)
- [Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline](https://mlsanity.com/paper/2301.12511/) (2023)
- [UniWorld: Autonomous Driving Pre-training via World Models](https://mlsanity.com/paper/2308.07234/) (2023)
- [LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection](https://mlsanity.com/paper/2206.07705/) (2022)
- [Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2303.01686/) (2023)
- [RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection](https://mlsanity.com/paper/2307.10249/) (2023)
- [MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts](https://mlsanity.com/paper/2302.10549/) (2023)
- [Fast-BEV: Towards Real-time On-vehicle Bird's-Eye View Perception](https://mlsanity.com/paper/2301.07870/) (2023)
- [A Simple Baseline for Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2208.10035/) (2022)
- [FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection](https://mlsanity.com/paper/2209.10733/) (2022)
- [Surround-View Vision-based 3D Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2302.06650/) (2023)
- [RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Network](https://mlsanity.com/paper/2409.04979/) (2024)
- [CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection](https://mlsanity.com/paper/2209.13507/) (2022)
- [SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection](https://mlsanity.com/paper/2308.13794/) (2023)
- [Towards Model Generalization for Monocular 3D Object Detection](https://mlsanity.com/paper/2205.11664/) (2022)
- [ZFusion: An Effective Fuser of Camera and 4D Radar for 3D Object Perception in Autonomous Driving](https://mlsanity.com/paper/2504.03438/) (2025)
- [WidthFormer: Toward Efficient Transformer-based BEV View Transformation](https://mlsanity.com/paper/2401.03836/) (2024)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [Multi-Spectral Image Stitching via Spatial Graph Reasoning](https://mlsanity.com/paper/2307.16741/) (2023)
- [Better Monocular 3D Detectors with LiDAR from the Past](https://mlsanity.com/paper/2404.05139/) (2024)
- [HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection](https://mlsanity.com/paper/2412.18884/) (2024)
- [All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles](https://mlsanity.com/paper/2510.26641/) (2025)
- [LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices](https://mlsanity.com/paper/2209.00961/) (2022)

## Abstract (arXiv)

3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding. Due to its low cost and high efficiency, multi-view 3D object detection has demonstrated promising application prospects. However, accurately detecting objects through perspective views in the 3D space is extremely difficult due to the lack of depth information. Recently, DETR3D introduces a novel 3D-2D query paradigm in aggregating multi-view images for 3D object detection and achieves state-of-the-art performance. In this paper, with intensive pilot experiments, we quantify the objects located at different regions and find that the "truncated instances" (i.e., at the border regions of each image) are the main bottleneck hindering the performance of DETR3D. Although it merges multiple features from two adjacent views in the overlapping regions, DETR3D still suffers from insufficient feature aggregation, thus missing the chance to fully boost the detection performance. In an effort to tackle the problem, we propose Graph-DETR3D to automatically aggregate multi-view imagery information through graph structure learning (GSL). It constructs a dynamic 3D graph between each object query and 2D feature maps to enhance the object representations, especially at the border regions. Besides, Graph-DETR3D benefits from a novel depth-invariant multi-scale training strategy, which maintains the visual depth consistency by simultaneously scaling the image size and the object depth. Extensive experiments on the nuScenes dataset demonstrate the effectiveness and efficiency of our Graph-DETR3D. Notably, our best model achieves 49.5 NDS on the nuScenes test leaderboard, achieving new state-of-the-art in comparison with various published image-view 3D object detectors.