☆ 3.8 Proceedings Paper

A Cylindrical Convolution Network for Dense Top-View Semantic Segmentation with LiDAR Point Clouds

COMPUTER VISION - ACCV 2022, PT VII (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Civil

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

Kunyu Peng et al.

Summary: In this paper, the authors introduce a multi-attention semantic segmentation model called MASS, specifically designed for dense top-view understanding of driving scenes. The model utilizes pillar- and occupancy features and incorporates three attention-based building blocks to generate dense 360 degrees segmentation masks. The experiments conducted on SemanticKITTI and nuScenes-LidarSeg demonstrate the effectiveness of the model, particularly in the context of 3D object detection.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data

Juncong Fei et al.

Summary: Semantic understanding is crucial for automated vehicles, and the SemanticKITTI dataset has spurred research on semantic segmentation of LiDAR point clouds in urban scenarios. PillarSegNet, a new approach, achieves a 10% performance gain over the state-of-the-art grid map method by outputting dense semantic grid maps through PointNet feature learning and 2D semantic segmentation in top view.

2021 32ND IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV) (2021)

Add to Collection

Article Robotics

Cross-View Semantic Segmentation for Sensing Surroundings

Bowen Pan et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Add to Collection

Proceedings Paper Automation & Control Systems

GndNet: Fast Ground Plane Estimation and Point Cloud Segmentation for Autonomous Vehicles

Anshul Paigwar et al.

2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud

Xin Kong et al.

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2019)

Add to Collection

Article Engineering, Civil

ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation

Eduardo Romera et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2018)

Add to Collection

A Cylindrical Convolution Network for Dense Top-View Semantic Segmentation with LiDAR Point Clouds

Related references

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data

Cross-View Semantic Segmentation for Sensing Surroundings

GndNet: Fast Ground Plane Estimation and Point Cloud Segmentation for Autonomous Vehicles

PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud

ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation

Export Citation

Share Paper