Deep learning for image and point cloud fusion in autonomous driving: A review

Y Cui, R Chen, W Chu, L Chen, D Tian… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… -based data fusion approaches that leverage both image and point cloud. This review gives
… and point cloud data processing. Followed by in-depth reviews of camera-LiDAR fusion

Intelligent surveillance of indoor environments based on computer vision and 3D point cloud fusion

MJ Gómez, F García, D Martín, A de la Escalera… - Expert Systems with …, 2015 - Elsevier
… matrix needed to align the source point cloud with target point cloud. This resultant point
cloud, source point cloud aligned, will be the target point cloud in the next mapping iteration. …

Deep fusionnet for point cloud semantic segmentation

F Zhang, J Fang, B Wah, P Torr - Computer Vision–ECCV 2020: 16th …, 2020 - Springer
… for accurate point-wise segmentation of large-scale point clouds, we develop a deep fusion
… “mini-PointNet” structure for point cloud representation and a novel fusion module (Fig. 2) for …

Real‐Time Vehicle Detection Algorithm Based on Vision and Lidar Point Cloud Fusion

H Wang, X Lou, Y Cai, Y Li, L Chen - Journal of Sensors, 2019 - Wiley Online Library
vision, this work proposes a real-time vehicle detection algorithm which fuses vision and lidar
point cloud … by the grid projection method using the lidar point cloud information. Then, the …

HybridFusion: LiDAR and Vision Cross-Source Point Cloud Fusion

Y Wang, S Bu, L Chen, Y Dong, K Li… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
… reconstructed point cloud as G and the LiDAR reconstructed point cloud as L. The point cloud
patches in G are defined as PG = 1pg1 ,pg2 ,pg3 ··· pgu l. In the same manner, point cloud

Rpvnet: A deep and efficient range-point-voxel fusion network for lidar point cloud segmentation

J Xu, R Zhang, J Dou, Y Zhu… - … on computer vision, 2021 - openaccess.thecvf.com
… We denote X as an arbitrary representation of a point cloud, and any form of point cloud
representation X can be seen as a mapping of the original points P. To note that,“projection” …

Fuseseg: Lidar point cloud segmentation fusing multi-modal data

G Krispel, M Opitz, G Waltner… - … of computer vision, 2020 - openaccess.thecvf.com
… task of point cloud segmentation to show the effectiveness and benefits of our fusion method.
… and applying an ImageNet CNN for early fusion, eg [11] or intermediate fusion, eg [13], ham…

Object detection based on fusion of sparse point cloud and image information

X Xu, L Zhang, J Yang, C Cao, Z Tan… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… The object detection algorithms can be categorized into 2-D image object detection, 3-D
point cloud object detection, and object detection based on laser and vision fusion. Image …

PANet: A point-attention based multi-scale feature fusion network for point cloud registration

Y Wu, Q Yao, X Fan, M Gong, W Ma… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
… registration is a critical task in many 3D computer vision studies, aiming to … point cloud with
another. In this paper, we propose PANet-a Point-Attention based multi-scale feature fusion

Multimodal token fusion for vision transformers

Y Wang, X Chen, L Cao, W Huang… - … on computer vision …, 2022 - openaccess.thecvf.com
… object detection (based on point cloud) and 2D object detection (… with 3D point cloud and 2D
image, we project each point to … Regarding the 3D object detection with point cloud as input, …