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 …

View-GCN: View-based graph convolutional network for 3D shape analysis

X Wei, R Yu, J Sun - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
View-based approach that recognizes 3D shape through its projected 2D images has
achieved state-of-the-art results for 3D shape recognition. The major challenge for view …

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 …

Self-supervised deep learning on point clouds by reconstructing space

J Sauder, B Sievers - Advances in Neural Information …, 2019 - proceedings.neurips.cc
Point clouds provide a flexible and natural representation usable in countless applications
such as robotics or self-driving cars. Recently, deep neural networks operating on raw point …

3D2SeqViews: Aggregating sequential views for 3D global feature learning by CNN with hierarchical attention aggregation

Z Han, H Lu, Z Liu, CM Vong, YS Liu… - … on Image Processing, 2019 - ieeexplore.ieee.org
Learning 3D global features by aggregating multiple views is important. Pooling is widely
used to aggregate views in deep learning models. However, pooling disregards a lot of …

A large-scale annotated mechanical components benchmark for classification and retrieval tasks with deep neural networks

S Kim, H Chi, X Hu, Q Huang, K Ramani - Computer Vision–ECCV 2020 …, 2020 - Springer
We introduce a large-scale annotated mechanical components benchmark for classification
and retrieval tasks named Mechanical Components Benchmark (MCB): a large-scale …

View inter-prediction gan: Unsupervised representation learning for 3d shapes by learning global shape memories to support local view predictions

Z Han, M Shang, YS Liu, M Zwicker - … of the AAAI conference on artificial …, 2019 - aaai.org
In this paper, we present a novel unsupervised representation learning approach for 3D
shapes, which is an important research challenge as it avoids the manual effort required for …

DeepSphere: a graph-based spherical CNN

M Defferrard, M Milani, F Gusset… - arxiv preprint arxiv …, 2020 - arxiv.org
Designing a convolution for a spherical neural network requires a delicate tradeoff between
efficiency and rotation equivariance. DeepSphere, a method based on a graph …

SeqViews2SeqLabels: Learning 3D global features via aggregating sequential views by RNN with attention

Z Han, M Shang, Z Liu, CM Vong, YS Liu… - … on Image Processing, 2018 - ieeexplore.ieee.org
Learning 3D global features by aggregating multiple views has been introduced as a
successful strategy for 3D shape analysis. In recent deep learning models with end-to-end …

Learning view-based graph convolutional network for multi-view 3d shape analysis

X Wei, R Yu, J Sun - IEEE Transactions on Pattern Analysis …, 2022 - ieeexplore.ieee.org
View-based approach that recognizes 3D shape through its projected 2D images has
achieved state-of-the-art results for 3D shape recognition. The major challenges are how to …