# VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention

arXiv: https://arxiv.org/abs/2203.09704 · HTML: https://mlsanity.com/paper/2203.09704/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 18 Mar 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [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)
- [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)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/1910.06528/) (2019)
- [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://mlsanity.com/paper/1903.08701/) (2019)
- [Improving 3D Object Detection with Channel-wise Transformer](https://mlsanity.com/paper/2108.10723/) (2021)
- [Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots](https://mlsanity.com/paper/1912.12791/) (2019)
- [Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection](https://mlsanity.com/paper/2005.09927/) (2020)
- [What You See is What You Get: Exploiting Visibility for 3D Object Detection](https://mlsanity.com/paper/1912.04986/) (2019)
- [StarNet: Targeted Computation for Object Detection in Point Clouds](https://mlsanity.com/paper/1908.11069/) (2019)
- [Spatially-sparse convolutional neural networks](https://mlsanity.com/paper/1409.6070/) (2014)
- [MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views](https://mlsanity.com/paper/2006.05518/) (2020)
- [MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data](https://mlsanity.com/paper/2104.10772/) (2021)

## Built on by (most cited first, 30 of 48)

- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks](https://mlsanity.com/paper/2207.05444/) (2022)
- [LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs](https://mlsanity.com/paper/2206.10555/) (2022)
- [Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection](https://mlsanity.com/paper/2406.10700/) (2024)
- [GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds](https://mlsanity.com/paper/2212.03010/) (2022)
- [Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images](https://mlsanity.com/paper/2205.13764/) (2022)
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/2305.04925/) (2023)
- [SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2403.05817/) (2024)
- [HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2310.20234/) (2023)
- [VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations](https://mlsanity.com/paper/2308.09916/) (2023)
- [Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds](https://mlsanity.com/paper/2207.00531/) (2022)
- [FastPillars: A Deployment-friendly Pillar-based 3D Detector](https://mlsanity.com/paper/2302.02367/) (2023)
- [GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training](https://mlsanity.com/paper/2305.08808/) (2023)
- [FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels](https://mlsanity.com/paper/2308.03755/) (2023)
- [GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2310.08261/) (2023)
- [LinK: Linear Kernel for LiDAR-based 3D Perception](https://mlsanity.com/paper/2303.16094/) (2023)
- [3D Vision with Transformers: A Survey](https://mlsanity.com/paper/2208.04309/) (2022)
- [BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios](https://mlsanity.com/paper/2212.05758/) (2022)
- [PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer](https://mlsanity.com/paper/2305.06621/) (2023)
- [AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset](https://mlsanity.com/paper/2306.00612/) (2023)
- [Human-centric Scene Understanding for 3D Large-scale Scenarios](https://mlsanity.com/paper/2307.14392/) (2023)
- [MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection](https://mlsanity.com/paper/2212.00442/) (2022)
- [VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2401.02702/) (2024)
- [Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder](https://mlsanity.com/paper/2405.18734/) (2024)
- [KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection](https://mlsanity.com/paper/2307.07942/) (2023)
- [Li3DeTr: A LiDAR based 3D Detection Transformer](https://mlsanity.com/paper/2210.15365/) (2022)
- [PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection](https://mlsanity.com/paper/2311.17770/) (2023)
- [DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation](https://mlsanity.com/paper/2210.05232/) (2022)
- [SparseDet: A Simple and Effective Framework for Fully Sparse LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2406.10907/) (2024)

## Abstract (arXiv)

Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved due to the sparsity and irregularity of LiDAR point clouds. Among existing strategies, multi-view methods have shown great promise by leveraging the more comprehensive information from both bird's eye view (BEV) and range view (RV). These multi-view methods either refine the proposals predicted from single view via fused features, or fuse the features without considering the global spatial context; their performance is limited consequently. In this paper, we propose to adaptively fuse multi-view features in a global spatial context via Dual Cross-VIew SpaTial Attention (VISTA). The proposed VISTA is a novel plug-and-play fusion module, wherein the multi-layer perceptron widely adopted in standard attention modules is replaced with a convolutional one. Thanks to the learned attention mechanism, VISTA can produce fused features of high quality for prediction of proposals. We decouple the classification and regression tasks in VISTA, and an additional constraint of attention variance is applied that enables the attention module to focus on specific targets instead of generic points. We conduct thorough experiments on the benchmarks of nuScenes and Waymo; results confirm the efficacy of our designs. At the time of submission, our method achieves 63.0% in overall mAP and 69.8% in NDS on the nuScenes benchmark, outperforming all published methods by up to 24% in safety-crucial categories such as cyclist. The source code in PyTorch is available at https://github.com/Gorilla-Lab-SCUT/VISTA