Learning 3D Information from 2D Images Using Aperture Rendering Generative Adversarial Networks toward Developing a Computer that “Understands the 3D World”

被引：0

作者：

Kaneko T. ^{[1
]}

机构：

[1] NTT Communication Science Laboratories, Japan

来源：

NTT Technical Review | 2022年 / 20卷 / 07期

关键词：

bokeh; depth; generative adversarial networks; unsupervised learning;

D O I：

10.53829/ntr202207ri1

中图分类号：

学科分类号：

摘要：

When people look at photos, they can estimate three-dimensional (3D) information, such as depth, from their experience and knowledge, but computers have difficulty in doing so because they cannot have such experience and knowledge. We spoke to Takuhiro Kaneko, a distinguished researcher who developed a novel deep learning model that can learn 3D information from standard 2D images such as those on the web. © 2022 Authors. All rights reserved.

引用

页码：6 / 9

页数：3

共 50 条

[21] Face recognition from 2D and 3D images
Wang, YJ
Chua, CS
Ho, YK
AUDIO- AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS, 2001, 2091 : 26 - 31
[22] Improving Object Detection in 2D Images Using a 3D World Model
Viggh, Herbert E. M.
Cho, Peter L.
Armstrong-Crews, Nicholas L.
Nam, Myra
Shah, Danelle C.
Brown, Geoffrey E.
MULTISENSOR, MULTISOURCE INFORMATION FUSION: ARCHITECTURES, ALGORITHMS, AND APPLICATIONS 2014, 2014, 9121
[23] 3D shape reconstruction from 2D images
Hirano, Daisuke
Funayama, Yusuke
Maekawa, Takashi
Computer-Aided Design and Applications, 2009, 6 (05): : 701 - 710
[24] From 2D images to 3D face geometry
Lengagne, R
Tarel, JP
Monga, O
PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, : 301 - 306
[25] Unified generative adversarial networks for multimodal segmentation from unpaired 3D medical images
Yuan, Wenguang
Wei, Jia
Wang, Jiabing
Ma, Qianli
Tasdizen, Tolga
MEDICAL IMAGE ANALYSIS, 2020, 64
[26] Rendering avatars in virtual reality: Integrating a 3D model with 2D images
Yang, YJ
Wang, XS
Chen, JX
COMPUTING IN SCIENCE & ENGINEERING, 2002, 4 (01) : 86 - 91
[27] Learning Adversarial 3D Model Generation with 2D Image Enhancer
Zhu, Jing
Xie, Jin
Fang, Yi
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 7615 - 7622
[28] Reconstruction of large-scale anisotropic 3D digital rocks from 2D shale images using generative adversarial network
Chi, Peng
Sun, Jianmeng
Zhang, Ran
Luo, Xin
Yan, Weichao
MARINE AND PETROLEUM GEOLOGY, 2024, 170
[29] From 2D to 3D
Steven De Feyter
Nature Chemistry, 2011, 3 (1) : 14 - 15
[30] 3D that everyone understands (3): Avoiding visual fatigue caused by viewing 3D images
Mizushina H.
Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 2011, 65 (03): : 297 - 301

← 1 2 3 4 5 →