Abstract
Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for pluralistic image completion - the task of generating multiple and diverse plausible solutions for image completion. A major challenge faced by learning-based approaches is that usually only one ground truth training instance per label. As such, sampling from conditional VAEs still leads to minimal diversity. To overcome this, we propose a novel and probabilistically principled framework with two parallel paths. One is a reconstructive path that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution. The other is a generative path for which the conditional prior is coupled to the distribution obtained in the reconstructive path. Both are supported by GANs. We also introduce a new short+long term attention layer that exploits distant relations among decoder and encoder features, improving appearance consistency. When tested on datasets with buildings (Paris), faces (CelebA-HQ), and natural images (ImageNet), our method not only generated higherquality completion results, but also with multiple and diverse plausible outputs.
Original language | English |
---|---|
Title of host publication | Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 |
Editors | Abhinav Gupta, Derek Hoiem, Gang Hua, Zhuowen Tu |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 1438-1447 |
Number of pages | 10 |
ISBN (Electronic) | 9781728132938 |
ISBN (Print) | 9781728132945 |
DOIs | |
Publication status | Published - 2019 |
Externally published | Yes |
Event | IEEE Conference on Computer Vision and Pattern Recognition 2019 - Long Beach, United States of America Duration: 16 Jun 2019 → 20 Jun 2019 Conference number: 32nd http://cvpr2019.thecvf.com/ https://ieeexplore.ieee.org/xpl/conhome/8938205/proceeding (Proceedings) |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
Volume | 2019-June |
ISSN (Print) | 1063-6919 |
Conference
Conference | IEEE Conference on Computer Vision and Pattern Recognition 2019 |
---|---|
Abbreviated title | CVPR 2019 |
Country/Territory | United States of America |
City | Long Beach |
Period | 16/06/19 → 20/06/19 |
Internet address |
Keywords
- Deep Learning
- Image and Video Synthesis