Ghost shadow removal in multi-layered video inpainting

被引：0

作者：

Shih, Timothy K. ^{[1
]}

Tang, Nick C. ^{[1
]}

Hwang, Jenq-Neng ^{[2
]}

机构：

[1] Tamkang Univ, Dept Comp Sci & Informat Engn, Taipei, Taiwan

[2] Univ Washington, Dept Elect Engn, Seattle, WA 98105 USA

来源：

2007 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-5 | 2007年

关键词：

video inpainting; motion map segmentation; object removal; image completion; digital inpainting;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Image inpainting or image completion removes objects from a photo and automatically produces a visually pleasant result. However, to remove objects from a video, the resulting video may have ghost shadows even each individual frame is inpainted properly. We use motion estimation algorithm to separate objects and backgrounds into several layers. Objects in separated layers are inpainted from back to front layers, with a consideration of the temporal continuity of motion segments among different frames. The resulting video is visually more pleasant with most ghost shadows removed. Interested readers are welcome to look at our demonstration website at http://www.mine.tku.edy.tw/demo.

引用

页码：1471 / +

页数：2

共 5 条

[1]

[Anonymous], P 7 IEEE WORKSH APPL

[2] Region filling and object removal by exemplar-based image inpainting [J].

Criminisi, A ;

Pérez, P ;

Toyama, K .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (09) :1200-1212

[3]

KEDAR A, 2005, 2005 IEEE INT C IM P

[4] A novel four-step search algorithm for fast block motion estimation [J].

Po, LM ;

Ma, WC .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 1996, 6 (03) :313-317

[5]

SHIH TK, 2006, 2006 ACM MULT C SANT

← 1 →