HOME > Detail View

Detail View

Video object removal by learning edge and optical flow

Video object removal by learning edge and optical flow

Material type
학위논문
Personal Author
김남주, 金楠周
Title Statement
Video object removal by learning edge and optical flow / Nam-joo Kim
Publication, Distribution, etc
Seoul :   Graduate School, Korea University,   2020  
Physical Medium
v, 45장 : 천연색삽화, 도표 ; 26 cm
기타형태 저록
Video Object Removal by Learning Edge and Optical Flow   (DCOLL211009)000000127350  
학위논문주기
학위논문(석사)-- 고려대학교 대학원: 컴퓨터·전파통신공학과, 2020. 2
학과코드
0510   6D36   1109  
General Note
지도교수: 이성환  
Bibliography, Etc. Note
참고문헌: 장 40-456
이용가능한 다른형태자료
PDF 파일로도 이용가능;   Requires PDF file reader(application/pdf)  
비통제주제어
computer vision,,
000 00000nam c2200205 c 4500
001 000046026313
005 20200428153738
007 ta
008 200106s2020 ulkad bmAC 000c eng
040 ▼a 211009 ▼c 211009 ▼d 211009
041 0 ▼a eng ▼b kor
085 0 ▼a 0510 ▼2 KDCP
090 ▼a 0510 ▼b 6D36 ▼c 1109
100 1 ▼a 김남주, ▼g 金楠周
245 1 0 ▼a Video object removal by learning edge and optical flow / ▼d Nam-joo Kim
260 ▼a Seoul : ▼b Graduate School, Korea University, ▼c 2020
300 ▼a v, 45장 : ▼b 천연색삽화, 도표 ; ▼c 26 cm
500 ▼a 지도교수: 이성환
502 0 ▼a 학위논문(석사)-- ▼b 고려대학교 대학원: ▼c 컴퓨터·전파통신공학과, ▼d 2020. 2
504 ▼a 참고문헌: 장 40-456
530 ▼a PDF 파일로도 이용가능; ▼c Requires PDF file reader(application/pdf)
653 ▼a computer vision
776 0 ▼t Video Object Removal by Learning Edge and Optical Flow ▼w (DCOLL211009)000000127350
900 1 0 ▼a Kim, Nam-joo, ▼e
900 1 0 ▼a 이성환, ▼g 李晟瑍, ▼e 지도교수
945 ▼a KLPA

Electronic Information

No. Title Service
1
Video object removal by learning edge and optical flow (14회 열람)
View PDF Abstract Table of Contents

Holdings Information

No. Location Call Number Accession No. Availability Due Date Make a Reservation Service
No. 1 Location Science & Engineering Library/Stacks(Thesis)/ Call Number 0510 6D36 1109 Accession No. 123063733 Availability Available Due Date Make a Reservation Service B M
No. 2 Location Science & Engineering Library/Stacks(Thesis)/ Call Number 0510 6D36 1109 Accession No. 123063734 Availability Available Due Date Make a Reservation Service B M

Contents information

Abstract

Video object removal, when given a video, aims to delete a particular object from the image and to plausibly fill the background in place. Image object removal has been studied tremendously since the rise of deep learning, whereas research in the video domain has not been studied due to challenging points of preserving spatio-temporal coherence and a large amount of computation. In spite of these difficulties, most media in real life are composed of video, so research is necessary.
In this work, we propose a network that performs video object removal using edge and optical flow information based on GAN network. The proposed network consists of three sub-networks; learning the edge information to create a background contour that is likely to be at the location of the object to be erased, translating the background pixel at the position of the object through the temporal relationship of the frames in the input video, and inpainting an image using edge information in a reduced empty space in preceding steps. 
Our method is evaluated on DAVIS datasets qualitatively and quantitatively, achieving the state-of-the-art performance in terms of object removal quality and speed. 

Table of Contents

Contents
1.  Introduction	- 1 -
2.  Related Works	- 5 -
2.1  Video Inpainting	- 6 -
2.2  Edge with Inpainting	- 12 -
2.3  Optical Flow	- 15 -
3.  The Proposed Method	- 17 -
3.1  Edge Generator	- 20 -
3.2  Flow Guided Frame Warping	- 23 -
3.3  Video Completion Network	- 25 -
4.  Experiments	- 28 -
4.1.  Implementation Details.	- 28 -
4.2.  The Quantitative evaluation with the State-of-the-art Methods	- 29 -
4.3.  The Qualitative evaluation with the State-of-the-art Methods	- 31 -
4.4.  User study	- 38 -
5.  Conclusion & Future Works	- 39 -
References	- 40 -