# Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection

arXiv: https://arxiv.org/abs/2211.13067 · HTML: https://mlsanity.com/paper/2211.13067/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 47 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 30 of 45)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [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)
- [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)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [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)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [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)
- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://mlsanity.com/paper/1907.10844/) (2019)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [LiDAR R-CNN: An Efficient and Universal 3D Object Detector](https://mlsanity.com/paper/2103.15297/) (2021)

## Built on by (most cited first, 14 of 14)

- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Spherical Transformer for LiDAR-based 3D Recognition](https://mlsanity.com/paper/2303.12766/) (2023)
- [SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling](https://mlsanity.com/paper/2401.04230/) (2024)
- [R2LDM: An Efficient 4D Radar Super-Resolution Framework Leveraging Diffusion Model](https://mlsanity.com/paper/2503.17097/) (2025)
- [What You See Is What You Detect: Towards better Object Densification in 3D detection](https://mlsanity.com/paper/2310.17842/) (2023)
- [FSMDet: Vision-guided feature diffusion for fully sparse 3D detector](https://mlsanity.com/paper/2409.06945/) (2024)
- [Enhanced 3D Object Detection via Diverse Feature Representations of 4D Radar Tensor](https://mlsanity.com/paper/2502.06114/) (2025)
- [Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2503.10579/) (2025)
- [C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation](https://mlsanity.com/paper/2607.01827/) (2026)
- [Multi-Object Tracking based on Imaging Radar 3D Object Detection](https://mlsanity.com/paper/2406.01011/) (2024)
- [RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion](https://mlsanity.com/paper/2504.13788/) (2025)
- [MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillation](https://mlsanity.com/paper/2509.13149/) (2025)
- [Shape-Prior-Based Point Cloud Completion for Single-Stage Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2606.00688/) (2026)
- [ATN3D: Density-Aware LiDAR-Radar Early 3D Object Detection Under Extreme Sparsity](https://mlsanity.com/paper/2606.09634/) (2026)

## Abstract (arXiv)

LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to efficiently boost 3D detection performance by learning to densify point clouds in latent space. Specifically, we first train a dense point 3D detector (DDet) with a dense point cloud as input and design a sparse point 3D detector (SDet) with a regular point cloud as input. Importantly, we formulate the lightweight plug-in S2D module and the point cloud reconstruction module in SDet to densify 3D features and train SDet to produce 3D features, following the dense 3D features in DDet. So, in inference, SDet can simulate dense 3D features from regular (sparse) point cloud inputs without requiring dense inputs. We evaluate our method on the large-scale Waymo Open Dataset and the Waymo Domain Adaptation Dataset, showing its high performance and efficiency over the state of the arts.