Object removal from complex videos using a few annotations

Autor: Thuc Trinh Le, Andrés Almansa, Yann Gousseau, Simon Masnou
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Zdroj: Computational Visual Media, Vol 5, Iss 3, Pp 267-291 (2019)
Druh dokumentu: article
ISSN: 2096-0433
2096-0662
DOI: 10.1007/s41095-019-0145-0
Popis: Abstract We present a system for the removal of objects from videos. As input, the system only needs a user to draw a few strokes on the first frame, roughly delimiting the objects to be removed. To the best of our knowledge, this is the first system allowing the semi-automatic removal of objects from videos with complex backgrounds. The key steps of our system are the following: after initialization, segmentation masks are first refined and then automatically propagated through the video. Missing regions are then synthesized using video inpainting techniques. Our system can deal with multiple, possibly crossing objects, with complex motions, and with dynamic textures. This results in a computational tool that can alleviate tedious manual operations for editing high-quality videos.
Databáze: Directory of Open Access Journals
Externí odkaz: