Object removal from complex videos using a few annotations - Télécom Paris Accéder directement au contenu
Article Dans Une Revue Computational Visual Media Année : 2019

Object removal from complex videos using a few annotations

Résumé

We present a system for the removal of objects from videos. As an 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 in 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. The 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.
Fichier principal
Vignette du fichier
_CVMJ__Removing_objects_from_video_with_a_few_strokes_publish.pdf (65.79 Mo) Télécharger le fichier
Vignette du fichier
Le2019-thumbnail.png (1.93 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Commentaire : graphical abstract
Loading...

Dates et versions

hal-02168653 , version 1 (28-06-2019)

Identifiants

Citer

Thuc Trinh Le, Andrés Almansa, Yann Gousseau, Simon Masnou. Object removal from complex videos using a few annotations. Computational Visual Media, 2019, 5, pp.267-291. ⟨10.1007/s41095-019-0145-0⟩. ⟨hal-02168653⟩

Relations

213 Consultations
64 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More