# SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds

arXiv: https://arxiv.org/abs/2006.04043 · HTML: https://mlsanity.com/paper/2006.04043/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2020.

## Built on by (most cited first, 27 of 27)

- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://mlsanity.com/paper/2212.00244/) (2022)
- [PointVector: A Vector Representation In Point Cloud Analysis](https://mlsanity.com/paper/2205.10528/) (2022)
- [PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer](https://mlsanity.com/paper/2305.06621/) (2023)
- [PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning](https://mlsanity.com/paper/2405.15214/) (2024)
- [Pattern-Aware Data Augmentation for LiDAR 3D Object Detection](https://mlsanity.com/paper/2112.00050/) (2021)
- [ORA3D: Overlap Region Aware Multi-view 3D Object Detection](https://mlsanity.com/paper/2207.00865/) (2022)
- [Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes](https://mlsanity.com/paper/2208.08621/) (2022)
- [Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection](https://mlsanity.com/paper/2307.00347/) (2023)
- [PointSee: Image Enhances Point Cloud](https://mlsanity.com/paper/2211.01664/) (2022)
- [SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data](https://mlsanity.com/paper/2406.10600/) (2024)
- [PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection](https://mlsanity.com/paper/2208.13414/) (2022)
- [Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2210.11237/) (2022)
- [DuEqNet: Dual-Equivariance Network in Outdoor 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2302.13577/) (2023)
- [Attention-based Part Assembly for 3D Volumetric Shape Modeling](https://mlsanity.com/paper/2304.10986/) (2023)
- [Angle Based Feature Learning in GNN for 3D Object Detection using Point Cloud](https://mlsanity.com/paper/2108.00780/) (2021)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)
- [SEFormer: Structure Embedding Transformer for 3D Object Detection](https://mlsanity.com/paper/2209.01745/) (2022)
- [Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection](https://mlsanity.com/paper/2403.01978/) (2024)
- [Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework](https://mlsanity.com/paper/2407.05769/) (2024)
- [PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection](https://mlsanity.com/paper/2408.14600/) (2024)
- [ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection](https://mlsanity.com/paper/2211.09518/) (2022)
- [SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanism](https://mlsanity.com/paper/2407.01239/) (2024)
- [PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilation](https://mlsanity.com/paper/2502.07822/) (2025)
- [Transferable Class Statistics and Multi-scale Feature Approximation for 3D Object Detection](https://mlsanity.com/paper/2508.11951/) (2025)
- [Point Virtual Transformer](https://mlsanity.com/paper/2602.06406/) (2026)

## Abstract (arXiv)

Accurate 3D object detection from point clouds has become a crucial component in autonomous driving. However, the volumetric representations and the projection methods in previous works fail to establish the relationships between the local point sets. In this paper, we propose Sparse Voxel-Graph Attention Network (SVGA-Net), a novel end-to-end trainable network which mainly contains voxel-graph module and sparse-to-dense regression module to achieve comparable 3D detection tasks from raw LIDAR data. Specifically, SVGA-Net constructs the local complete graph within each divided 3D spherical voxel and global KNN graph through all voxels. The local and global graphs serve as the attention mechanism to enhance the extracted features. In addition, the novel sparse-to-dense regression module enhances the 3D box estimation accuracy through feature maps aggregation at different levels. Experiments on KITTI detection benchmark demonstrate the efficiency of extending the graph representation to 3D object detection and the proposed SVGA-Net can achieve decent detection accuracy.