Visual attention methods in deep learning: An in-depth survey
Inspired by the human cognitive system, attention is a mechanism that imitates the human
cognitive awareness about specific information, amplifying critical details to focus more on …
cognitive awareness about specific information, amplifying critical details to focus more on …
Pu-transformer: Point cloud upsampling transformer
Given the rapid development of 3D scanners, point clouds are becoming popular in AI-
driven machines. However, point cloud data is inherently sparse and irregular, causing …
driven machines. However, point cloud data is inherently sparse and irregular, causing …
Transformers in 3d point clouds: A survey
Transformers have been at the heart of the Natural Language Processing (NLP) and
Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring …
Computer Vision (CV) revolutions. The significant success in NLP and CV inspired exploring …
Partglot: Learning shape part segmentation from language reference games
We introduce PartGlot, a neural framework and associated architectures for learning
semantic part segmentation of 3D shape geometry, based solely on part referential …
semantic part segmentation of 3D shape geometry, based solely on part referential …
Three-dimensional point cloud segmentation based on context feature for sheet metal part boundary recognition
Y Li, Y Wang, Y Liu - IEEE Transactions on Instrumentation and …, 2023 - ieeexplore.ieee.org
Point cloud is widely available in the manufacturing system with the continuous
development of 3-D sensors. Accurate point cloud segmentation can automatically identify …
development of 3-D sensors. Accurate point cloud segmentation can automatically identify …
Transformer-based global PointPillars 3D object detection method
L Zhang, H Meng, Y Yan, X Xu - Electronics, 2023 - mdpi.com
The PointPillars algorithm can detect vehicles, pedestrians, and cyclists on the road, and is
widely used in the field of environmental awareness in autonomous driving. However, its …
widely used in the field of environmental awareness in autonomous driving. However, its …
Research Progress of Lightweight Neural Network Convolution Design.
MA Jinlin, Z Yu, MA Ziping… - Journal of Frontiers of …, 2022 - search.ebscohost.com
Traditional neural networks have the disadvantages of over-reliance on hardware resources
and high requirements for application equipment performance. Therefore, they cannot be …
and high requirements for application equipment performance. Therefore, they cannot be …
Energy-based residual latent transport for unsupervised point cloud completion
Unsupervised point cloud completion aims to infer the whole geometry of a partial object
observation without requiring partial-complete correspondence. Differing from existing …
observation without requiring partial-complete correspondence. Differing from existing …
Robust Point Cloud Registration Network for Complex Conditions
R Hao, Z Wei, X He, K Zhu, J He, J Wang, M Li… - Sensors, 2023 - mdpi.com
Point cloud registration is widely used in autonomous driving, SLAM, and 3D reconstruction,
and it aims to align point clouds from different viewpoints or poses under the same …
and it aims to align point clouds from different viewpoints or poses under the same …
End-to-end point cloud geometry compression and analysis with sparse tensor
With the rapid development of deep learning, encoded objects such as images, videos, and
point cloud objects are increasingly used in downstream tasks optimized by deep learning …
point cloud objects are increasingly used in downstream tasks optimized by deep learning …