Please use this identifier to cite or link to this item:
Title: Pluralistic image completion
Authors: Zheng, Chuanxia
Cham, Tat-Jen
Cai, Jianfei
Keywords: Engineering::Computer science and engineering
Issue Date: 2019
Source: Zheng, C., Cham, T.-J., & Cai, J. (2019). Pluralistic image completion. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1438-1447. doi:10.1109/CVPR.2019.00153
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 higher-quality completion results, but also with multiple and diverse plausible outputs.
ISBN: 9781728132938
DOI: 10.1109/CVPR.2019.00153
Rights: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IMI Conference Papers

Files in This Item:
File Description SizeFormat 
Pluralistic image completion.pdf7.94 MBAdobe PDFThumbnail

Citations 1

Updated on Jan 23, 2023

Web of ScienceTM
Citations 1

Updated on Jan 19, 2023

Page view(s)

Updated on Jan 28, 2023

Download(s) 50

Updated on Jan 28, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.