HOME > 상세정보

상세정보

Video object removal by learning edge and optical flow

Video object removal by learning edge and optical flow

자료유형
학위논문
개인저자
김남주, 金楠周
서명 / 저자사항
Video object removal by learning edge and optical flow / Nam-joo Kim
발행사항
Seoul :   Graduate School, Korea University,   2020  
형태사항
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  
일반주기
지도교수: 이성환  
서지주기
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

전자정보

No. 원문명 서비스
1
Video object removal by learning edge and optical flow (14회 열람)
PDF 초록 목차

소장정보

No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 과학도서관/학위논문서고/ 청구기호 0510 6D36 1109 등록번호 123063733 도서상태 대출가능 반납예정일 예약 서비스 B M
No. 2 소장처 과학도서관/학위논문서고/ 청구기호 0510 6D36 1109 등록번호 123063734 도서상태 대출가능 반납예정일 예약 서비스 B M

컨텐츠정보

초록

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. 

목차

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 -