Review of multi-view 3D object recognition methods based on deep learning

S Qi, X Ning, G Yang, L Zhang, P Long, W Cai, W Li - Displays, 2021 - Elsevier
Abstract Three-dimensional (3D) object recognition is widely used in automated driving,
medical image analysis, virtual/augmented reality, artificial intelligence robots, and other …

A review on deep learning approaches for 3D data representations in retrieval and classifications

AS Gezawa, Y Zhang, Q Wang, L Yunqi - IEEE access, 2020 - ieeexplore.ieee.org
Deep learning approach has been used extensively in image analysis tasks. However,
implementing the methods in 3D data is a bit complex because most of the previously …

Rotationnet: Joint object categorization and pose estimation using multiviews from unsupervised viewpoints

A Kanezaki, Y Matsushita… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Abstract We propose a Convolutional Neural Network (CNN)-based model``RotationNet,''
which takes multi-view images of an object as input and jointly estimates its pose and object …

A survey on deep learning advances on different 3D data representations

E Ahmed, A Saint, AER Shabayek… - arXiv preprint arXiv …, 2018 - arxiv.org
3D data is a valuable asset the computer vision filed as it provides rich information about the
full geometry of sensed objects and scenes. Recently, with the availability of both large 3D …

Meshwalker: Deep mesh understanding by random walks

A Lahav, A Tal - ACM Transactions on Graphics (TOG), 2020 - dl.acm.org
Most attempts to represent 3D shapes for deep learning have focused on volumetric grids,
multi-view images and point clouds. In this paper we look at the most popular representation …

Multiview generative adversarial network and its application in pearl classification

Q Xuan, Z Chen, Y Liu, H Huang… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
This paper focuses on automatic pearl classification by adopting deep learning method,
using multiview pearl images. Traditionally, in order to get a satisfying classification result …

Multi-view saliency guided deep neural network for 3-D object retrieval and classification

HY Zhou, AA Liu, WZ Nie, J Nie - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
In this paper, we propose the multi-view saliency guided deep neural network (MVSG-DNN)
for 3D object retrieval and classification. This method mainly consists of three key modules …

Rotationnet for joint object categorization and unsupervised pose estimation from multi-view images

A Kanezaki, Y Matsushita… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
We propose a Convolutional Neural Network (CNN)-based model “RotationNet,” which
takes multi-view images of an object as input and jointly estimates its pose and object …

Orthographicnet: A deep transfer learning approach for 3-d object recognition in open-ended domains

SH Kasaei - IEEE/ASME Transactions on Mechatronics, 2020 - ieeexplore.ieee.org
Nowadays, service robots are appearing more and more in our daily life. For this type of
robot, open-ended object category learning and recognition is necessary since no matter …

General-purpose deep point cloud feature extractor

M Dominguez, R Dhamdhere, A Petkar… - 2018 IEEE winter …, 2018 - ieeexplore.ieee.org
Depth sensors used in autonomous driving and gaming systems often report back 3D point
clouds. The lack of structure from these sensors does not allow these systems to take …