RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI등재

    시점 변경을 위한 깊이 정보를 이용한 홀채움 기법 = Depth-guided Hole-filling Algorithm for View Synthesis

    한글로보기

    https://www.riss.kr/link?id=A108686729

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
    • 오류접수

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    The significance of precise image inpainting for image view synthesis has grown in recent years due to the rapid development of autonomous driving or XR (eXtended Reality) devices or robotics. Numerous studies have been conducted on image inpainting during this time, but they have involved intricate procedures and neglected depth information. This paper introduces a novel and straightforward hole-filling algorithm that leverages local depth information. We generate direction vector map based on the local depth information for each hole pixel and utilize the map for the image inpainting. We perform experiments using two distinct simple inpainting methods and compare them with the method augmented by depth information, evaluating both qualitative and quantitative metrics. The results of these experiments demonstrate improvements in numerical accuracy and plausibility.
    번역하기

    The significance of precise image inpainting for image view synthesis has grown in recent years due to the rapid development of autonomous driving or XR (eXtended Reality) devices or robotics. Numerous studies have been conducted on image inpainting d...

    The significance of precise image inpainting for image view synthesis has grown in recent years due to the rapid development of autonomous driving or XR (eXtended Reality) devices or robotics. Numerous studies have been conducted on image inpainting during this time, but they have involved intricate procedures and neglected depth information. This paper introduces a novel and straightforward hole-filling algorithm that leverages local depth information. We generate direction vector map based on the local depth information for each hole pixel and utilize the map for the image inpainting. We perform experiments using two distinct simple inpainting methods and compare them with the method augmented by depth information, evaluating both qualitative and quantitative metrics. The results of these experiments demonstrate improvements in numerical accuracy and plausibility.

    더보기

    참고문헌 (Reference)

    1 문희정, "증강현실 기반의 인포메이션 실감체험을 위한 앱 콘텐츠 개발" 한국멀티미디어학회 23 (23): 1428-1434, 2020

    2 S. M. Muddala, "Virtual View Synthesis Using Layered Depth Image Generation and Depth-Based Inpainting for Filling Disocclusions and Translucent Disocclusions" 38 : 351-366, 2016

    3 S. M. Muddala, "Spatio-Temporal Consistent Depth-Image-Based Rendering Using Layered Depth Image and Inpainting" 1-19, 2016

    4 Y. Chen, "Research on Image Inpainting Algorithm of Improved GAN based on Two-Discriminations Networks" 51 : 3460-3474, 2021

    5 A. Lugmayr, "Repaint: In-Painting Using Denoising Diffusion Probabilistic Models" 11461-11471, 2022

    6 A. Criminisi, "Region Filling and Object Removal by Exemplar-bas ed Image Inpainting" 13 (13): 1200-1212, 2004

    7 X. He, "Non-Local and Multi-Scale Mechanisms for Image Inpainting" 21 (21): 3281-, 2021

    8 G. Liu, "Image Inpainting for Irregular Holes using Partial Convolutions" 85-100, 2018

    9 M. Bertalmio, "Image Inpainting" 417-424, 2000

    10 J. Habigt, "Hole-Filling Algorithms for Depth-Image-Based Rendering" Technische Universität München 2020

    1 문희정, "증강현실 기반의 인포메이션 실감체험을 위한 앱 콘텐츠 개발" 한국멀티미디어학회 23 (23): 1428-1434, 2020

    2 S. M. Muddala, "Virtual View Synthesis Using Layered Depth Image Generation and Depth-Based Inpainting for Filling Disocclusions and Translucent Disocclusions" 38 : 351-366, 2016

    3 S. M. Muddala, "Spatio-Temporal Consistent Depth-Image-Based Rendering Using Layered Depth Image and Inpainting" 1-19, 2016

    4 Y. Chen, "Research on Image Inpainting Algorithm of Improved GAN based on Two-Discriminations Networks" 51 : 3460-3474, 2021

    5 A. Lugmayr, "Repaint: In-Painting Using Denoising Diffusion Probabilistic Models" 11461-11471, 2022

    6 A. Criminisi, "Region Filling and Object Removal by Exemplar-bas ed Image Inpainting" 13 (13): 1200-1212, 2004

    7 X. He, "Non-Local and Multi-Scale Mechanisms for Image Inpainting" 21 (21): 3281-, 2021

    8 G. Liu, "Image Inpainting for Irregular Holes using Partial Convolutions" 85-100, 2018

    9 M. Bertalmio, "Image Inpainting" 417-424, 2000

    10 J. Habigt, "Hole-Filling Algorithms for Depth-Image-Based Rendering" Technische Universität München 2020

    11 D. Scharstein, "High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth" 31-42, 2014

    12 J. Yu, "Generative Image Inpainting with Contextual Attention" 5505-5514, 2018

    13 H.Y. Huang, "Fast Hole Filling for View Synthesis in Free Viewpoint Video" 9 (9): 906-, 2020

    14 Y. Chen, "FFTI:Image Inpainting Algorithm Via Features Fusion and Two-steps Inpainting" 91 (91): 2023

    15 A. Telea, "An Image Inpainting Technique Based on the Fast Marching Method" 9 (9): 23-34, 2004

    16 Z. Zhang, "A Flexible New Technique for Camera Calibration" 22 (22): 1330-1334, 2000

    17 M. L. Shih, "3D Photography Using Context-Aware Layered Depth Inpainting" 8028-8038, 2020

    더보기

    동일학술지(권/호) 다른 논문

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼