Exemplar-based image inpainting using an affine invariant similarity measure

Fedorov, Vadim; Arias Martínez, Pablo; Facciolo Furlan, Gabriele; Ballester, Coloma

doi:http://dx.doi.org/10.1007/978-3-319-64870-5_22

Exemplar-based image inpainting using an affine invariant similarity measure

Citation

Fedorov V, Arias P, Facciolo G, Ballester C. Exemplar-based image inpainting using an affine invariant similarity measure. In: Braz J, Magnenat-Thalmann N, Richard P, Linsen L, Telea A, Battiato S, Imai F. Computer Vision, Imaging and Computer Graphics Theory and Applications. 11th International Joint Conference, VISIGRAPP: International Joint Conference on Computer Vision, Imaging and Computer Graphics; 2016 Feb 27-29; Rome, Italy. Cham: Springer; 2016. p. 454-74. DOI: 10.1007/978-3-319-64870-5_22

Abstract

Patch-based approaches are used in state-of-the-art methods for image inpainting. This paper presents a new method for exemplar-based image inpainting using transformed patches. The transformation is determined for each patch in a fully automatic way from a surrounding texture content. We build upon a recent affine invariant patch similarity measure that performs an appropriate patch comparison by automatically adapting the size and shape of the patches. As a consequence, it intrinsically extends the set of available source patches to copy information from. We incorporate this measure into a variational formulation for inpainting and present a numerical algorithm for optimizing it. We show that our method can be applied to complete a perspectively distorted texture as well as to automatically inpaint one view of a scene using other view of the same scene as a source. We present experimental results both for gray and color images, and a comparison with some exemplar-based image inpainting methods.

Description

Comunicació presentada a 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016), celebrat del 27 al 29 de febrer de 2016 a Roma, Itàlia.