Paper Info
Title
Salient object segmentation for image composition: A case study of group dinner photo
Abstract
AbstractAbstractThe rocketing number of photos shared on social media leads to the increasing demand for photo editing. We here focus on a specific scenario - group dinner photo and tackle two user-demanding problems - to add a person or replace the tabletop. The target objects are determined according to the saliency detection results. We developed a novel application to solve these problems. With our system, non-professional users can accomplish semantic editing within a few seconds, including inserting human and tidying up tabletops. Our system contributes to the state-of-the-art by (1) efficiently selecting the saliency area by its semantic meaning, (2) accurately compositing the salient content with the target image, based on the contextual knowledge. The context refers to the key factors, including occlusion and artifacts during the composition. The feedback from users shows that the authenticity of inserting human is satisfying. A comparative study shows that our system can more efficiently produce pictures with comparable quality as those edited by professional editing software in the tidying up tabletops work.
Year
DOI
Venue
2021
10.1016/j.neucom.2020.06.127
Periodicals
Keywords
DocType
Volume
Saliency Detection, Image Composition, Object selection, Image Inpainting
Journal
453
Issue
ISSN
Citations 
C
0925-2312
0
PageRank 
References 
Authors
0.34
0
8
Name
Order
Citations
PageRank
Tianxiang Ren100.34
Lianhui Lin200.34
Shihui Guo34415.97
Juncong Lin410520.73
Minghong Liao59018.97
Shujie Deng600.34
Panpan Xu772.80
Yinyu Nie824.15