32
IRUS TotalDownloads
Altmetric
3D Object reconstruction from a single depth view with adversarial learning
File | Description | Size | Format | |
---|---|---|---|---|
1708.07969.pdf | Accepted version | 2.85 MB | Adobe PDF | View/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 |