Skip navigation
Skip navigation

Image Completion from Low-level Learning

Zhu, Bin; Li, Hongdong


We present a learning-based approach to complete the missing parts of an image. Besides the conventional adopted image continuity and coherency heuristics, learnt image patches are used to better regularize the completion result. Through the learning process from a collection of commonly encountered natural images, we built a synthetic world consisting of scenes and their corresponding images. We further model the inter-patch relationships with a Markov Network. A belief propagation scheme is...[Show more]

CollectionsANU Research Publications
Date published: 2005
Type: Conference paper
Source: Proceedings of the Digital Imaging Computing: Techniques and Applications (DICTA 2005)
DOI: 10.1109/DICTA.2005.1578135


File Description SizeFormat Image
01_Zhu_Image_Completion_from_2005.pdf523.65 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator