Data to 13 Oct 2026

STD: Sparse-to-Dense 3D Object Detector for Point Cloud

arXiv 1907.10471 ↗First posted 22 Jul 2019cs.CVcited by 282

Not on the map. Why?

Abstract (arXiv)

We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a high recall with less computation compared with prior works. Then, PointsPool is applied for generating proposal features by transforming their interior point features from sparse expression to compact representation, which saves even more computation time. In box prediction, which is the second stage, we implement a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance. We conduct experiments on KITTI dataset, and evaluate our method in terms of 3D object and Bird's Eye View (BEV) detection. Our method outperforms other state-of-the-arts by a large margin, especially on the hard set, with inference speed more than 10 FPS.

Key facts. Cited by 282 papers in the map (data through 13 Oct 2026). First posted on arXiv 22 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 69; 2022: 77; 2023: 72; 2024: 32; 2025: 23; 2026: 9.

282 papers.

Sort:

By area:

2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 446
2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
2021Voxel Transformer for 3D Object Detectioncited by 247
2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 187
2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
2021Multimodal Virtual Point 3D Detectioncited by 166

38 more

2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
2021Offboard 3D Object Detection from Point Cloud Sequencescited by 145
2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
2021Improving 3D Object Detection with Channel-wise Transformercited by 108
20213D Object Detection for Autonomous Driving: A Surveycited by 106
2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 94
2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
20213D-MAN: 3D Multi-frame Attention Network for Object Detectioncited by 73
2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
2022Point Density-Aware Voxels for LiDAR 3D Object Detectioncited by 70
2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
2022MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detectioncited by 65
2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
2023Fully Sparse 3D Occupancy Predictioncited by 63
2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
2022CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Cloudscited by 58
2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57

50 most cited of 282 All 282 (JSON)