Video Inpainting of Complex Scenes

Alasdair Newson (1, 2) , Andrés Almansa (3) , Matthieu Fradet (1) , Yann Gousseau (2) , Patrick Pérez (4)

1 Technicolor R & I [Cesson Sévigné]
2 Télécom ParisTech
3 LTCI - Laboratoire Traitement et Communication de l'Information
4 Technicolor [Cesson Sévigné]

We propose an automatic video inpainting algorithm which relies on the optimisation of a global, patch-based functional. Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background. Furthermore, we achieve this in an order of magnitude less execution time with respect to the state-of-the-art. We are also able to achieve good quality results on high definition videos. Finally, we provide specific algorithmic details to make implementation of our algorithm as easy as possible. The resulting algorithm requires no segmentation or manual input other than the definition of the inpainting mask, and can deal with a wider variety of situations than is handled by previous work.

Mots clés: Video inpainting; patch-based; video textures; moving background

Domaines: Traitement des images [eess.IV]

Alasdair Newson, Andrés Almansa, Matthieu Fradet, Yann Gousseau, Patrick Pérez. Video Inpainting of Complex Scenes. 2014. ⟨hal-00937795v1⟩