# VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection

arXiv: https://arxiv.org/abs/2304.01054 · HTML: https://mlsanity.com/paper/2304.01054/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 39 references that are in the map.
- First posted on arXiv 3 Apr 2023.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving](https://mlsanity.com/paper/2205.09743/) (2022)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)

## Built on by (most cited first, 5 of 5)

- [PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors](https://mlsanity.com/paper/2403.09079/) (2024)
- [Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection](https://mlsanity.com/paper/2310.15670/) (2023)
- [GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping](https://mlsanity.com/paper/2307.09472/) (2023)
- [Towards Unified 3D Object Detection via Algorithm and Data Unification](https://mlsanity.com/paper/2402.18573/) (2024)
- [UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair](https://mlsanity.com/paper/2603.19616/) (2026)

## Abstract (arXiv)

In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks. However, their performance in multi-view 3D object detection remains inferior to the state-of-the-art (SOTA) of convolutional neural network based detectors. In this work, we investigate this issue from the perspective of bird's-eye-view (BEV) feature generation. Specifically, we examine the BEV feature generation method employed by the transformer-based SOTA, BEVFormer, and identify its two limitations: (i) it only generates attention weights from BEV, which precludes the use of lidar points for supervision, and (ii) it aggregates camera view features to the BEV through deformable sampling, which only selects a small subset of features and fails to exploit all information. To overcome these limitations, we propose a novel BEV feature generation method, dual-view attention, which generates attention weights from both the BEV and camera view. This method encodes all camera features into the BEV feature. By combining dual-view attention with the BEVFormer architecture, we build a new detector named VoxelFormer. Extensive experiments are conducted on the nuScenes benchmark to verify the superiority of dual-view attention and VoxelForer. We observe that even only adopting 3 encoders and 1 historical frame during training, VoxelFormer still outperforms BEVFormer significantly. When trained in the same setting, VoxelFormer can surpass BEVFormer by 4.9% NDS point. Code is available at: https://github.com/Lizhuoling/VoxelFormer-public.git.