Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

PatchNet: a patch-based image representation for interactive library-driven image editing

Hu, Shi-Min ORCID:, Zhang, Fang-Lue, Wang, Miao, Martin, Ralph Robert and Wang, Jue 2013. PatchNet: a patch-based image representation for interactive library-driven image editing. ACM Transactions on Graphics 32 (6) , 196. 10.1145/2508363.2508381

[thumbnail of PatchNet.pdf]
Download (4MB) | Preview


We introduce PatchNets, a compact, hierarchical representation describing structural and appearance characteristics of image regions, for use in image editing. In a PatchNet, an image region with coherent appearance is summarized by a graph node, associated with a single representative patch, while geometric relationships between different regions are encoded by labelled graph edges giving contextual information. The hierarchical structure of a PatchNet allows a coarse-to-fine description of the image. We show how this PatchNet representation can be used as a basis for interactive, library-driven, image editing. The user draws rough sketches to quickly specify editing constraints for the target image. The system then automatically queries an image library to find semantically-compatible candidate regions to meet the editing goal. Contextual image matching is performed using the PatchNet representation, allowing suitable regions to be found and applied in a few seconds, even from a library containing thousands of images.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources
Additional Information: PDF uploaded in accordance with publisher's policy [accessed 06/05/2015] © ACM, 2013. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Graphics, VOL 32, ISS 6, 2013
Publisher: Association for Computing Machinery
ISSN: 0730-0301
Funders: EPSRC
Last Modified: 08 Nov 2023 03:54

Citation Data

Cited 52 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics