# HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection

arXiv: https://arxiv.org/abs/2104.00902 · HTML: https://mlsanity.com/paper/2104.00902/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 2 Apr 2021.

## Builds on (most cited first, 30 of 39)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [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)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [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)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection](https://mlsanity.com/paper/2004.12636/) (2020)
- [Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering](https://mlsanity.com/paper/1904.04357/) (2019)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://mlsanity.com/paper/1903.01864/) (2019)
- [Fast Point R-CNN](https://mlsanity.com/paper/1908.02990/) (2019)
- [Ask Me Anything: Dynamic Memory Networks for Natural Language Processing](https://mlsanity.com/paper/1506.07285/) (2015)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)

## Built on by (most cited first, 30 of 47)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection](https://mlsanity.com/paper/2205.07403/) (2022)
- [CenterFormer: Center-based Transformer for 3D Object Detection](https://mlsanity.com/paper/2209.05588/) (2022)
- [AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds](https://mlsanity.com/paper/2112.09205/) (2021)
- [DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.08531/) (2022)
- [Learning Occupancy for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.15694/) (2023)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer](https://mlsanity.com/paper/2208.05216/) (2022)
- [MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2308.05988/) (2023)
- [OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data](https://mlsanity.com/paper/2204.06577/) (2022)
- [3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detection](https://mlsanity.com/paper/2410.01647/) (2024)
- [Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation](https://mlsanity.com/paper/2309.17336/) (2023)
- [PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection](https://mlsanity.com/paper/2311.17770/) (2023)
- [Real-Time And Robust 3D Object Detection with Roadside LiDARs](https://mlsanity.com/paper/2207.05200/) (2022)
- [Multi-Modality Task Cascade for 3D Object Detection](https://mlsanity.com/paper/2107.04013/) (2021)
- [Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network](https://mlsanity.com/paper/2207.05497/) (2022)
- [PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection](https://mlsanity.com/paper/2211.08055/) (2022)
- [Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving](https://mlsanity.com/paper/2302.03914/) (2023)
- [Diffusion-based 3D Object Detection with Random Boxes](https://mlsanity.com/paper/2309.02049/) (2023)
- [ImpDet: Exploring Implicit Fields for 3D Object Detection](https://mlsanity.com/paper/2203.17240/) (2022)
- [Multi-Modal 3D Object Detection by Box Matching](https://mlsanity.com/paper/2305.07713/) (2023)
- [A Review of 3D Object Detection with Vision-Language Models](https://mlsanity.com/paper/2504.18738/) (2025)
- [PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection](https://mlsanity.com/paper/2208.13414/) (2022)
- [MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer](https://mlsanity.com/paper/2308.16518/) (2023)
- [Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR](https://mlsanity.com/paper/2508.00744/) (2025)
- [LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation](https://mlsanity.com/paper/2304.01519/) (2023)
- [DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection](https://mlsanity.com/paper/2305.15219/) (2023)
- [V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Network](https://mlsanity.com/paper/2310.06603/) (2023)
- [GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data](https://mlsanity.com/paper/2310.20319/) (2023)

## Abstract (arXiv)

We address the problem of 3D object detection, that is, estimating 3D object bounding boxes from point clouds. 3D object detection methods exploit either voxel-based or point-based features to represent 3D objects in a scene. Voxel-based features are efficient to extract, while they fail to preserve fine-grained 3D structures of objects. Point-based features, on the other hand, represent the 3D structures more accurately, but extracting these features is computationally expensive. We introduce in this paper a novel single-stage 3D detection method having the merit of both voxel-based and point-based features. To this end, we propose a new convolutional neural network (CNN) architecture, dubbed HVPR, that integrates both features into a single 3D representation effectively and efficiently. Specifically, we augment the point-based features with a memory module to reduce the computational cost. We then aggregate the features in the memory, semantically similar to each voxel-based one, to obtain a hybrid 3D representation in a form of a pseudo image, allowing to localize 3D objects in a single stage efficiently. We also propose an Attentive Multi-scale Feature Module (AMFM) that extracts scale-aware features considering the sparse and irregular patterns of point clouds. Experimental results on the KITTI dataset demonstrate the effectiveness and efficiency of our approach, achieving a better compromise in terms of speed and accuracy.