Paper Info
Title
SIFT-guided multi-resolution video inpainting with innovative scheduling mechanism and irregular patch matching.
Abstract
An effective video inpainting method for repairing damaged video, or removing such unwanted objects as burned-in subtitles in TV programs.A classifier and scheduler scheme to prioritize inpainting order, which significantly affects the inpainting results.A multi-resolution approach with SIFT guiding the inpainting path to resolve uncertainty in large inpainting regions.Irregular patch-filling to better preserve visually significant areas and speed up the process. Effective video inpainting that maintains both temporal and spatial continuity is required in many applications. This research presents a new video inpainting algorithm targeted at achieving a better tradeoff between visual quality and computational complexity. The inpainting regions in video frames are classified into two types, i.e., structure and smooth. A scheduling mechanism considering texture data amount, inpainting confidence and motion vector uniformity is proposed to determine an appropriate processing order of inpainting points. A novel patch comparison function to evaluate the similarity and an irregular patch-filling method are developed to ensure decent visual quality and faster inpainting speed. The ideas of multi-resolution processing and scale-invariant feature transform are further adopted such that larger inpainting areas can still be processed well. To evaluate the effectiveness of the proposed algorithm, inpainting on television programs and video clips from literature is tested. The experimental results demonstrate better performance when compared with traditional methods.
Year
DOI
Venue
2016
10.1016/j.ins.2016.08.091
Information Sciences
Keywords
Field
DocType
Inpainting,Video,Multi-resolution,Motion vector field,Sift,Scheduling
Scale-invariant feature transform,Computer vision,Computer science,Scheduling (computing),Inpainting,Artificial intelligence,Feature transform,Classifier (linguistics),Computational complexity theory,Speedup,Motion vector
Journal
Volume
Issue
ISSN
373
C
0020-0255
Citations 
PageRank 
References 
3
0.40
30
Authors
3
Name
Order
Citations
PageRank
Tien-Ying Kuo114819.24
Po-Chyi Su218821.53
Yun-Ping Kuan330.40