# VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

arXiv: https://arxiv.org/abs/2303.11301 · HTML: https://mlsanity.com/paper/2303.11301/

## Key facts

- Cited by 222 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 63 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 30 of 55)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [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)
- [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)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)

## Built on by (most cited first, 30 of 222)

- [GenAD: Generative End-to-End Autonomous Driving](https://mlsanity.com/paper/2402.11502/) (2024)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [UniPAD: A Universal Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2310.08370/) (2023)
- [Far3D: Expanding the Horizon for Surround-view 3D Object Detection](https://mlsanity.com/paper/2308.09616/) (2023)
- [A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook](https://mlsanity.com/paper/2401.01454/) (2024)
- [Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection](https://mlsanity.com/paper/2406.10700/) (2024)
- [FocalFormer3D : Focusing on Hard Instance for 3D Object Detection](https://mlsanity.com/paper/2308.04556/) (2023)
- [IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection](https://mlsanity.com/paper/2403.15241/) (2024)
- [PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm](https://mlsanity.com/paper/2310.08586/) (2023)
- [Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis](https://mlsanity.com/paper/2403.01439/) (2024)
- [PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2308.16896/) (2023)
- [SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2403.05817/) (2024)
- [SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving](https://mlsanity.com/paper/2404.06892/) (2024)
- [A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering](https://mlsanity.com/paper/2306.06211/) (2023)
- [HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2310.20234/) (2023)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model](https://mlsanity.com/paper/2306.02245/) (2023)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [LION: Linear Group RNN for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2407.18232/) (2024)
- [BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection](https://mlsanity.com/paper/2312.01696/) (2023)
- [FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels](https://mlsanity.com/paper/2308.03755/) (2023)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [GaussianAD: Gaussian-Centric End-to-End Autonomous Driving](https://mlsanity.com/paper/2412.10371/) (2024)
- [Fully Sparse Fusion for 3D Object Detection](https://mlsanity.com/paper/2304.12310/) (2023)
- [LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection](https://mlsanity.com/paper/2401.15865/) (2024)
- [Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection](https://mlsanity.com/paper/2304.12315/) (2023)
- [Uni3DETR: Unified 3D Detection Transformer](https://mlsanity.com/paper/2310.05699/) (2023)
- [Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives](https://mlsanity.com/paper/2402.02968/) (2024)
- [Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2407.07995/) (2024)
- [MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection](https://mlsanity.com/paper/2408.05945/) (2024)

## Abstract (arXiv)

3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and efficient framework, with no need for sparse-to-dense conversion or NMS post-processing. Our method achieves a better speed-accuracy trade-off than other mainframe detectors on the nuScenes dataset. For the first time, we show that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2 benchmarks validate the effectiveness of our approach. Without bells and whistles, our model outperforms all existing LIDAR methods on the nuScenes tracking test benchmark.