Error Compensation Framework for Flow-Guided Video Inpainting

被引:13
|
作者
Kang, Jaeyeon [1 ]
Oh, Seoung Wug [2 ]
Kim, Seon Joo [1 ]
机构
[1] Yonsei Univ, Seoul, South Korea
[2] Adobe, San Jose, CA USA
来源
关键词
Video inpainting; Object removal; Video restoration;
D O I
10.1007/978-3-031-19784-0_22
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The key to video inpainting is to use correlation information from as many reference frames as possible. Existing flow-based propagation methods split the video synthesis process into multiple steps: flow completion -> pixel propagation -> synthesis. However, there is a significant drawback that the errors in each step continue to accumulate and amplify in the next step. To this end, we propose an Error Compensation Framework for Flow-guided Video Inpainting (ECFVI), which takes advantage of the flow-based method and offsets its weaknesses. We address the weakness with the newly designed flow completion module and the error compensation network that exploits the error guidance map. Our approach greatly improves the temporal consistency and the visual quality of the completed videos. Experimental results show the superior performance of our proposed method with the speed up of x6, compared to the state-of-the-art methods. In addition, we present a new benchmark dataset for evaluation by supplementing the weaknesses of existing test datasets.
引用
下载
收藏
页码:375 / 390
页数:16
相关论文
共 50 条
  • [31] Recurrent Flow-Guided Semantic Forecasting
    Terwilliger, Adam M.
    Brazil, Garrick
    Liu, Xiaoming
    2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 1703 - 1712
  • [32] A flow-guided streamline seeding strategy
    Verma, V
    Kao, D
    Pang, A
    VISUALIZATION 2000, PROCEEDINGS, 2000, : 163 - 170
  • [33] FLOW-GUIDED CATHETERIZATION - PERFORMANCE, COMPLICATIONS
    KRESS, P
    SEIBOLD, H
    WIESHAMMER, S
    SCHMIDT, A
    HAERER, W
    AHNEFELD, FW
    STAUCH, M
    HOMBACH, V
    HERZ KREISLAUF, 1988, 20 (12): : 511 - 517
  • [34] Flow2Mesh: A flow-guided data-driven mesh adaptation framework
    Yu, Jian
    Lyu, Hongqiang
    Xu, Ran
    Ouyang, Wenxuan
    Liu, Xuejun
    PHYSICS OF FLUIDS, 2024, 36 (03)
  • [35] Flow-Guided Temporal-Spatial Network for HEVC Compressed Video Quality Enhancement
    Meng, Xiandong
    Deng, Xuan
    Zhu, Shuyuan
    Liu, Shuaicheng
    Zeng, Bing
    2020 DATA COMPRESSION CONFERENCE (DCC 2020), 2020, : 384 - 384
  • [36] FLOW-GUIDED DEFORMABLE ATTENTION NETWORK FOR FAST ONLINE VIDEO SUPER-RESOLUTION
    Yang, Xi
    Zhang, Xindong
    Zhang, Lei
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 390 - 394
  • [37] IMPROVED INJECTION CHAMBER FOR FLOW-GUIDED CATHETERS
    OREILLY, GV
    KLEEFIELD, J
    SVENDSEN, PA
    WANG, AM
    AMERICAN JOURNAL OF NEURORADIOLOGY, 1984, 5 (02) : 212 - 213
  • [38] FLOW-GUIDED CATHETERIZATION IN RESPIRATORY-DISEASES
    SEIBOLD, H
    KRESS, P
    WIESHAMMER, S
    HERZ KREISLAUF, 1990, 22 (04): : 151 - 154
  • [39] An efficient framework for image/video inpainting
    Wang, Miaohui
    Yan, Bo
    Ngan, King Ngi
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2013, 28 (07) : 753 - 762
  • [40] Flow-guided feature enhancement network for video-based person re-identification
    Gong, Weichao
    Yan, Bo
    Lin, Chuming
    NEUROCOMPUTING, 2020, 383 : 295 - 302