%0 Conference Paper %F Oral %T Affine Invariant Self-Similarity for Exemplar-Based Inpainting %+ DITIC, universitat Pompeu Fabra %+ imagine [Marne-la-Vallée] %+ École des Ponts ParisTech (ENPC) %+ Laboratoire d'Informatique Gaspard-Monge (LIGM) %A Fedorov, Vadim %A Arias, Pablo %A Facciolo, Gabriele %A Ballester, Coloma %< avec comité de lecture %B VISAPP %C Rome, Italy %8 2016 %D 2016 %Z Computer Science [cs]/Image Processing [eess.IV] %Z Computer Science [cs]/Signal and Image Processing %Z Computer Science [cs]/Modeling and Simulation %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Conference papers %X This paper presents a new method for exemplar-based image inpainting using transformed patches. We build upon a recent affine invariant self-similarity measure which automatically transforms patches to compare them in an appropriate manner. As a consequence, it intrinsically extends the set of available source patches to copy information from. When comparing two patches, instead of searching for the appropriate patch transformation in a highly dimensional parameter space, our approach allows us to determine a single transformation from the texture content in both patches. We incorporate the affine invariant similarity measure in a variational formulation for inpainting and present an algorithm together with experimental results illustrating this approach. %G English %2 https://enpc.hal.science/hal-01240846/document %2 https://enpc.hal.science/hal-01240846/file/VISAPP_2016__Inpainting__camera_ready__.pdf %L hal-01240846 %U https://enpc.hal.science/hal-01240846 %~ ENPC %~ CNRS %~ LIGM_A3SI %~ PARISTECH %~ LIGM %~ CV_LIGM %~ IMAGINE %~ TDS-MACS %~ ENPC_ONLY %~ ESIEE-PARIS %~ UNIV-EIFFEL %~ UPEM-UNIVEIFFEL %~ ESIEE-UNIVEIFFEL %~ TEST3-HALCNRS