mlsanityData to 7 Oct 2026

A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding

arXiv 2103.04056 ↗First posted 6 Mar 2021cs.CV cs.ROcited by 17

Not on the map. Why?

Abstract (arXiv)

Detecting dynamic objects and predicting static road information such as drivable areas and ground heights are crucial for safe autonomous driving. Previous works studied each perception task separately, and lacked a collective quantitative analysis. In this work, we show that it is possible to perform all perception tasks via a simple and efficient multi-task network. Our proposed network, LidarMTL, takes raw LiDAR point cloud as inputs, and predicts six perception outputs for 3D object detection and road understanding. The network is based on an encoder-decoder architecture with 3D sparse convolution and deconvolution operations. Extensive experiments verify the proposed method with competitive accuracies compared to state-of-the-art object detectors and other task-specific networks. LidarMTL is also leveraged for online localization. Code and pre-trained model have been made available at https://github.com/frankfengdi/LidarMTL.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 6 Mar 2021.

Builds on

25 of 42 references.

References · 25

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  3. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  6. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  9. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  10. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  11. 2017Sparsity Invariant CNNscited by 325
  12. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
13 more
  1. 2017Submanifold Sparse Convolutional Networkscited by 223
  2. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  3. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  4. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  5. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  6. 2016MultiNet: Real-time Joint Semantic Reasoning for Autonomous Drivingcited by 90
  7. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  8. 2020SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detectioncited by 66
  9. 2020Convolutional Recurrent Network for Road Boundary Extractioncited by 33
  10. 2019Deep Multi-Sensor Lane Detectioncited by 30
  11. 2019UrbanLoco: A Full Sensor Suite Dataset for Mapping and Localization in Urban Scenescited by 17
  12. 2020Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detectioncited by 17
  13. 2018Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentationcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 5; 2024: 7; 2025: 1.

17 papers.

Sort:

  1. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  2. 2021Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Modelscited by 41
  3. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  4. 2022DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detectioncited by 20
  5. 2023FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibrationcited by 13
  6. 2023LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perceptioncited by 11
  7. 2025M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Drivingcited by 10
  8. 2024A Point-Based Approach to Efficient LiDAR Multi-Task Perceptioncited by 9
  9. 2024Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shiftcited by 9
  10. 2024Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Surveycited by 9
  11. 2022LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Networkcited by 8
  12. 2024UniVision: A Unified Framework for Vision-Centric 3D Perceptioncited by 7
5 more
  1. 2024Panoptic Perception for Autonomous Driving: A Surveycited by 4
  2. 2023LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Drivingcited by 2
  3. 2024LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detectioncited by 2
  4. 2023Instance-aware 3D Semantic Segmentation powered by Shape Generators and Classifierscited by 0
  5. 20243D Object Visibility Prediction in Autonomous Drivingcited by 0