Deep learning on 3D point clouds
A point cloud is a set of points defined in a 3D metric space. Point clouds have become one
of the most significant data formats for 3D representation and are gaining increased …
of the most significant data formats for 3D representation and are gaining increased …
Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community
In recent years, deep learning (DL), a rebranding of neural networks (NNs), has risen to the
top in numerous areas, namely computer vision (CV), speech recognition, and natural …
top in numerous areas, namely computer vision (CV), speech recognition, and natural …
[PDF][PDF] 神经网络七十年: 回顾与展望
焦李成, 杨淑媛, 刘芳, 王士刚, 冯志玺 - 计算机学报, 2016 - cjc.ict.ac.cn
Hodykin-Huxley 方程, 感知器模型与自适应滤波器, 再到六十年代的自组织映射网络,
神经认知机, 自适应共振网络, 许多神经计算模型都发展成为信号处理, 计算机视觉 …
神经认知机, 自适应共振网络, 许多神经计算模型都发展成为信号处理, 计算机视觉 …
Voxelnet: End-to-end learning for point cloud based 3d object detection
Accurate detection of objects in 3D point clouds is a central problem in many applications,
such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To …
such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To …
Foldingnet: Point cloud auto-encoder via deep grid deformation
Recent deep networks that directly handle points in a point set, eg, PointNet, have been
state-of-the-art for supervised learning tasks on point clouds such as classification and …
state-of-the-art for supervised learning tasks on point clouds such as classification and …
Splatnet: Sparse lattice networks for point cloud processing
We present a network architecture for processing point clouds that directly operates on a
collection of points represented as a sparse set of samples in a high-dimensional lattice …
collection of points represented as a sparse set of samples in a high-dimensional lattice …
Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud
We address semantic segmentation of road-objects from 3D LiDAR point clouds. In
particular, we wish to detect and categorize instances of interest, such as cars, pedestrians …
particular, we wish to detect and categorize instances of interest, such as cars, pedestrians …
Mvx-net: Multimodal voxelnet for 3d object detection
Many recent works on 3D object detection have focused on designing neural network
architectures that can consume point cloud data. While these approaches demonstrate …
architectures that can consume point cloud data. While these approaches demonstrate …
A review of vehicle detection techniques for intelligent vehicles
Z Wang, J Zhan, C Duan, X Guan… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Robust and efficient vehicle detection is an important task of environment perception of
intelligent vehicles, which directly affects the behavior decision-making and motion planning …
intelligent vehicles, which directly affects the behavior decision-making and motion planning …
Voxnet: A 3d convolutional neural network for real-time object recognition
D Maturana, S Scherer - 2015 IEEE/RSJ international …, 2015 - ieeexplore.ieee.org
Robust object recognition is a crucial skill for robots operating autonomously in real world
environments. Range sensors such as LiDAR and RGBD cameras are increasingly found in …
environments. Range sensors such as LiDAR and RGBD cameras are increasingly found in …