32
IRUS Total
Downloads
  Altmetric

3D Object reconstruction from a single depth view with adversarial learning

File Description SizeFormat 
1708.07969.pdfAccepted version2.85 MBAdobe PDFView/Open
Title: 3D Object reconstruction from a single depth view with adversarial learning
Authors: Yang, B
Wen, H
Wang, S
Clark, R
Markham, A
Trigoni, N
Item Type: Conference Paper
Abstract: In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike the existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid by filling in the occluded/missing regions. The key idea is to combine the generative capabilities of autoencoders and the conditional Generative Adversarial Networks (GAN) framework, to infer accurate and fine-grained 3D structures of objects in high-dimensional voxel space. Extensive experiments on large synthetic datasets show that the proposed 3D-RecGAN significantly outperforms the state of the art in single view 3D object reconstruction, and is able to reconstruct unseen types of objects. Our code and data are available at: https://github.com/Yang7879/3D-RecGAN.
Issue Date: 23-Jan-2017
Date of Acceptance: 1-Dec-2016
URI: http://hdl.handle.net/10044/1/71005
DOI: https://doi.org/10.1109/ICCVW.2017.86
ISBN: 9781538610343
ISSN: 2473-9936
Publisher: IEEE
Start Page: 679
End Page: 688
Journal / Book Title: 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017)
Copyright Statement: © 2017 IEEE.
Conference Name: 16th IEEE International Conference on Computer Vision (ICCV)
Keywords: Science & Technology
Technology
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Computer Science
Engineering
Science & Technology
Technology
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Computer Science
Engineering
Publication Status: Published
Start Date: 2017-11-15
Finish Date: 2017-10-29
Conference Place: Venice, Italy
Open Access location: https://arxiv.org/pdf/1708.07969.pdf
Online Publication Date: 2018-01-23
Appears in Collections:Computing