A Survey on Data-Driven Video Completion

• Published in: Computer graphics forum Vol. 34; no. 6; pp. 60 - 85
• Main Authors: Ilan, S., Shamir, A.
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.09.2015
• Subjects: Analysis; Coherence; computational photography; Computer graphics; Digital video; Equivalence; Foundations; I.3.3 [Computer Graphics]: Picture/Image Generation; I.3.3 [Computer Graphics]: Picture/Image Generation; I.4.4 [Image Processing and Computer Vision]: Restoration; I.4.9 [Image Processing and Computer Vision]: Applications; I.4.4 [Image Processing and Computer Vision]: Restoration; I.4.9 [Image Processing and Computer Vision]: Applications; Image processing systems; image/video completion; image/video editing; inpainting; object removal; Readers; rig removal; State of the art; Studies; Temporal logic; Two dimensional; video repairing
• ISSN: 0167-7055; 1467-8659
• DOI: 10.1111/cgf.12518

Image completion techniques aim to complete selected regions of an image in a natural looking manner with little or no user interaction. Video Completion, the space–time equivalent of the image completion problem, inherits and extends both the difficulties and the solutions of the original 2D problem, but also imposes new ones—mainly temporal coherency and space complexity (videos contain significantly more information than images). Data‐driven approaches to completion have been established as a favoured choice, especially when large regions have to be filled. In this survey, we present the current state of the art in data‐driven video completion techniques. For unacquainted researchers, we aim to provide a broad yet easy to follow introduction to the subject (including an extensive review of the image completion foundations) and early guidance to the challenges ahead. For a versed reader, we offer a comprehensive review of the contemporary techniques, sectioned out by their approaches to key aspects of the problem. Image completion techniques aim to complete selected regions of an image in a natural looking manner with little or no user interaction.Video Completion, the space–time equivalent of the image completion problem, inherits and extends both the difficulties and the solutions of the original 2D problem, but also imposes new ones—mainly temporal coherency and space complexity (videos contain significantly more information than images). Data‐driven approaches to completion have been established as a favoured choice, especially when large regions have to be filled. In this survey, we present the current state of the art in data‐driven video completion techniques. For unacquainted researchers, we aim to provide a broad yet easy to follow introduction to the subject (including an extensive review of the image completion foundations) and early guidance to the challenges ahead. For a versed reader, we offer a comprehensive review of the contemporary techniques, sectioned out by their approaches to key aspects of the problem.