Exemplar-Based Image Inpainting using an Affine Invariant Similarity Measure

Vadim Fedorov (1) , Pablo Arias (2) , Gabriele Facciolo (3) , Coloma Ballester (1)

1 DITIC, universitat Pompeu Fabra
2 CMLA - Centre de Mathématiques et de Leurs Applications
3 Departament de Tecnologies de la Informació i les Comunicacions

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.

Domaines: Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]; Modélisation et simulation; Vision par ordinateur et reconnaissance de formes [cs.CV]

Vadim Fedorov, Pablo Arias, Gabriele Facciolo, Coloma Ballester. Exemplar-Based Image Inpainting using an Affine Invariant Similarity Measure. Computer Vision, Imaging and Computer Graphics Theory and Applications 11th International Joint Conference, VISIGRAPP 2016, Rome, Italy, February 27 – 29, 2016, Revised Selected Papers , 2017, Communications in Computer and Information Science book series, ⟨10.1007/978-3-319-64870-5_22⟩. ⟨hal-01829625⟩