Point Cloud Generation Using Deep Adversarial Local Features for Augmented and Mixed Reality Contentsopen access
- Authors
- Lim, S.; Shin, M.; Paik, Joonki
- Issue Date
- Feb-2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Augmented reality (AR); Feature extraction; Generative Adversarial Network (GAN).; Generative adversarial networks; Image reconstruction; Mixed reality (MR); Point cloud; Point cloud compression; Shape; Solid modeling; Three-dimensional displays
- Citation
- IEEE Transactions on Consumer Electronics, v.68, no.1, pp 69 - 76
- Pages
- 8
- Journal Title
- IEEE Transactions on Consumer Electronics
- Volume
- 68
- Number
- 1
- Start Page
- 69
- End Page
- 76
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/54914
- DOI
- 10.1109/TCE.2022.3141093
- ISSN
- 0098-3063
1558-4127
- Abstract
- We present a generative model-based point cloud generation method using deep adversarial local features. The proposed generative adversarial network (GAN) can reduce computational load and increase the accuracy in three-dimensional (3D) acquisition, reconstruction, and rendering processes. To train the proposed GAN, we first optimize the latent space using an autoencoder to extract local features. The training process provides an accurate estimation of local context from the latent variables and robust point cloud generation. The main contribution of this work is a novel deep learning-based 3D point cloud generation, which significantly reduces computational load to render augmented reality (AR) and mixed reality (MR) contents. Additional contribution in the deep learning field is twofold: i) The autoencoder in the proposed network avoids the vanishing gradient problem using hierarchically linked features in different layers, and ii) the complexity of the network is significantly reduced by removing the transformation network that estimates the affine transformation matrix of the point cloud. Author
- Files in This Item
-
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.