University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Disentangling Structure and Aesthetics for Style-aware Image Completion

Gilbert, Andrew, Collomosse, John, Jin, H and Price, B (2018) Disentangling Structure and Aesthetics for Style-aware Image Completion In: CVPR 2018, 18 - 22 June 2018, Salt Lake City, Utah, USA.

CVPR_Style_Fill.pdf - Accepted version Manuscript

Download (35MB) | Preview


Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images. We propose a non-parametric in-painting algorithm that enforces both structural and aesthetic (style) consistency within the resulting image. Our contributions are two-fold: 1) we explicitly disentangle image structure and style during patch search and selection to ensure a visually consistent look and feel within the target image. 2) we perform adaptive stylization of patches to conform the aesthetics of selected patches to the target image, so harmonizing the integration of selected patches into the final composition. We show that explicit consideration of visual style during in-painting delivers excellent qualitative and quantitative results across the varied image styles and content, over the Places2 scene photographic dataset and a challenging new in-painting dataset of artwork derived from BAM!

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Jin, H
Price, B
Date : 2018
Copyright Disclaimer : Copyright 2018 The Author(s)
Depositing User : Melanie Hughes
Date Deposited : 18 Apr 2018 10:09
Last Modified : 16 Jan 2019 19:09

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800