CIRI: Curricular inactivation for residue-aware one-shot video inpainting

Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated f...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHENG, Weiying, XU, Cheng, XU, Xuemiao, LIU, Wenxi, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8535
https://ink.library.smu.edu.sg/context/sis_research/article/9538/viewcontent/Zheng_CIRI_Curricular_Inactivation_for_Residue_aware_One_shot_Video_Inpainting_ICCV_2023_paper__1_.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9538
record_format dspace
spelling sg-smu-ink.sis_research-95382024-03-27T03:20:51Z CIRI: Curricular inactivation for residue-aware one-shot video inpainting ZHENG, Weiying XU, Cheng XU, Xuemiao LIU, Wenxi HE, Shengfeng Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated first frame is provided. A naive solution is to propagate the initial target to the other frames with techniques like object tracking. In this context, the main obstacles are the unreliable propagation and the partially inpainted artifacts due to the inaccurate mask. For the former problem, we propose curricular inactivation to replace the hard masking mechanism for indicating the inpainting target, which is robust to erroneous predictions in long-term video inpainting. For the latter, we explore the properties of inpainting residue and present an online residue removal method in an iterative detect-and-refine manner. Extensive experiments on several real-world datasets demonstrate the quantitative and qualitative superiorities of our proposed method in one-shot video inpainting. More importantly, our method is extremely flexible that can be integrated with arbitrary traditional inpainting models, activating them to perform the reliable one-shot video inpainting task. Video demonstrations can be found in our supplement, and our code can be found at https://github.com/Arise-zwy/CIRI. 2023-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8535 info:doi/10.1109/ICCV51070.2023.01196 https://ink.library.smu.edu.sg/context/sis_research/article/9538/viewcontent/Zheng_CIRI_Curricular_Inactivation_for_Residue_aware_One_shot_Video_Inpainting_ICCV_2023_paper__1_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Video inpainting Curricular Inactivation CIRI Computer Sciences Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Video inpainting
Curricular Inactivation
CIRI
Computer Sciences
Graphics and Human Computer Interfaces
spellingShingle Video inpainting
Curricular Inactivation
CIRI
Computer Sciences
Graphics and Human Computer Interfaces
ZHENG, Weiying
XU, Cheng
XU, Xuemiao
LIU, Wenxi
HE, Shengfeng
CIRI: Curricular inactivation for residue-aware one-shot video inpainting
description Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated first frame is provided. A naive solution is to propagate the initial target to the other frames with techniques like object tracking. In this context, the main obstacles are the unreliable propagation and the partially inpainted artifacts due to the inaccurate mask. For the former problem, we propose curricular inactivation to replace the hard masking mechanism for indicating the inpainting target, which is robust to erroneous predictions in long-term video inpainting. For the latter, we explore the properties of inpainting residue and present an online residue removal method in an iterative detect-and-refine manner. Extensive experiments on several real-world datasets demonstrate the quantitative and qualitative superiorities of our proposed method in one-shot video inpainting. More importantly, our method is extremely flexible that can be integrated with arbitrary traditional inpainting models, activating them to perform the reliable one-shot video inpainting task. Video demonstrations can be found in our supplement, and our code can be found at https://github.com/Arise-zwy/CIRI.
format text
author ZHENG, Weiying
XU, Cheng
XU, Xuemiao
LIU, Wenxi
HE, Shengfeng
author_facet ZHENG, Weiying
XU, Cheng
XU, Xuemiao
LIU, Wenxi
HE, Shengfeng
author_sort ZHENG, Weiying
title CIRI: Curricular inactivation for residue-aware one-shot video inpainting
title_short CIRI: Curricular inactivation for residue-aware one-shot video inpainting
title_full CIRI: Curricular inactivation for residue-aware one-shot video inpainting
title_fullStr CIRI: Curricular inactivation for residue-aware one-shot video inpainting
title_full_unstemmed CIRI: Curricular inactivation for residue-aware one-shot video inpainting
title_sort ciri: curricular inactivation for residue-aware one-shot video inpainting
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8535
https://ink.library.smu.edu.sg/context/sis_research/article/9538/viewcontent/Zheng_CIRI_Curricular_Inactivation_for_Residue_aware_One_shot_Video_Inpainting_ICCV_2023_paper__1_.pdf
_version_ 1795302167225040896