CASIA OpenIR  > 智能感知与计算研究中心
Free-Form Image Inpainting via Contrastive Attention Network
Xin,Ma1,2,3; Xiaoqiang Zhou2,3,4; Huaibo Huang1,3; Zhenhua Chai2; Xiaolin Wei2; Ran He1,3
2021-01
Conference NameInternational Conference on Pattern Recognition (ICPR)
Conference DateJan 10-15, 2021
Conference PlaceMilan, Italy
PublisherIEEE
Abstract

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with sophisticated learning tasks. Specifically, in image inpainting tasks, masks with any shapes can appear anywhere in images (i.e., free-form masks) which form complex patterns. It is difficult for encoders to capture such powerful representations under this complex situation. To tackle this problem, we propose a self-supervised Siamese inference network to improve the robustness and generalization. It can encode contextual semantics from full resolution images and obtain more discriminative representations. we further propose a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine both the restored and known regions in a smooth way. This multi-scale architecture is beneficial for decoding discriminative representations learned by encoders into images layer by layer.  In this way, unknown regions will be filled naturally from outside to inside. Qualitative and quantitative experiments on multiple datasets, including facial and natural datasets (i.e., Celeb-HQ, Pairs Street View, Places2 and ImageNet), demonstrate that our proposed method outperforms state-of-the-art methods in generating high-quality inpainting results. 

Indexed ByEI
Sub direction classification图像视频处理与分析
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/44842
Collection智能感知与计算研究中心
Corresponding AuthorRan He
Affiliation1.School of Artificial Intelligence,University of Chinese Academy of Sciences
2.Vision Intelligence Center, AI Platform, Meituandianping Group
3.NLPR & CEBSIT, CASIA
4.University of Science and Technology of China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Xin,Ma,Xiaoqiang Zhou,Huaibo Huang,et al. Free-Form Image Inpainting via Contrastive Attention Network[C]:IEEE,2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
Free-Form Image Inpa(2477KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xin,Ma]'s Articles
[Xiaoqiang Zhou]'s Articles
[Huaibo Huang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xin,Ma]'s Articles
[Xiaoqiang Zhou]'s Articles
[Huaibo Huang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xin,Ma]'s Articles
[Xiaoqiang Zhou]'s Articles
[Huaibo Huang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Free-Form Image Inpainting via Contrastive Attention Network_Ma et al_2021.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.