scispace - formally typeset
Journal ArticleDOI

Exemplar-Based Video Inpainting Without Ghost Shadow Artifacts by Maintaining Temporal Continuity

Reads0
Chats0
TLDR
An exemplar-based image inpainting algorithm is extended by incorporating an improved patch matching strategy for video inPainting, which produces very few ldquoghost shadows,rdquo which were produced by most image in painting algorithms directly applied on video.
Abstract
Image inpainting or image completion is the technique that automatically restores/completes removed areas in an image. When dealing with a similar problem in video, not only should a robust tracking algorithm be used, but the temporal continuity among video frames also needs to be taken into account, especially when the video has camera motions such as zooming and tilting. In this paper, we extend an exemplar-based image inpainting algorithm by incorporating an improved patch matching strategy for video inpainting. In our proposed algorithm, different motion segments with different temporal continuity call for different candidate patches, which are used to inpaint holes after a selected video object is tracked and removed. The proposed new video inpainting algorithm produces very few ldquoghost shadows,rdquo which were produced by most image inpainting algorithms directly applied on video. Our experiments use different types of videos, including cartoon, video from games, and video from digital camera with different camera motions. Our demonstration at http://member.mine.tku.edu.tw/www/T_CSVT/web/shows the promising results.

read more

Citations
More filters
Proceedings ArticleDOI

Deep Flow-Guided Video Inpainting

TL;DR: This work first synthesizes a spatially and temporally coherent optical flow field across video frames using a newly designed Deep Flow Completion network, then uses the synthesized flow fields to guide the propagation of pixels to fill up the missing regions in the video.
Journal ArticleDOI

Video Inpainting by Jointly Learning Temporal Structure and Spatial Details

TL;DR: A novel deep learning architecture is proposed which contains two subnetworks: a temporal structure inference network and a spatial detail recovering network, which jointly trains both sub-networks in an end-to-end manner.
Book ChapterDOI

Background inpainting for videos with dynamic objects and a free-moving camera

TL;DR: This work provides experimental validation with several real-world video sequences to demonstrate that, unlike in previous work, inpainting videos shot with free-moving cameras does not necessarily require estimation of absolute camera positions and per-frame per-pixel depth maps.
Journal ArticleDOI

Video Inpainting With Short-Term Windows: Application to Object Removal and Error Concealment

TL;DR: Experiments with several challenging video sequences show that the proposed video inpainting method provides visually pleasing results for object removal, error concealment, and background reconstruction context.
Journal ArticleDOI

How Not to Be Seen — Object Removal from Videos of Crowded Scenes

TL;DR: This work proposes a new approach to video completion that can deal with complex scenes containing dynamic background and non‐periodical moving objects, and builds upon the idea that the spatio‐temporal hole left by a removed object can be filled with data available on other regions of the video where the occluded objects were visible.
References
More filters
Journal ArticleDOI

Mean shift: a robust approach toward feature space analysis

TL;DR: It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.
Journal ArticleDOI

Region filling and object removal by exemplar-based image inpainting

TL;DR: The simultaneous propagation of texture and structure information is achieved by a single, efficient algorithm that combines the advantages of two approaches: exemplar-based texture synthesis and block-based sampling process.
Journal ArticleDOI

A novel four-step search algorithm for fast block motion estimation

TL;DR: Simulation results show that the proposed 4SS performs better than the well-known three- step search and has similar performance to the new three-step search (N3SS) in terms of motion compensation errors.
Proceedings ArticleDOI

Scene completion using millions of photographs

TL;DR: A new image completion algorithm powered by a huge database of photographs gathered from the Web, requiring no annotations or labelling by the user, that can generate a diverse set of results for each input image and allow users to select among them.
Journal ArticleDOI

Space-Time Completion of Video

TL;DR: This paper presents a new framework for the completion of missing information based on local structures that poses the task of completion as a global optimization problem with a well-defined objective function and derives a new algorithm to optimize it.
Related Papers (5)