Learning Reaction-Diffusion Models for Image Inpainting

Wei Yu, Stefan Heber, Thomas Pock

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

In this paper we present a trained diffusion model for image inpainting based on the structural similarity measure. The proposed diffusion model uses several parametrized linear filters and influence functions. Those parameters are learned in a loss based approach, where we first perform a greedy training before conducting a joint training to further improve the inpainting performance. We provide a detailed comparison to state-of-the-art inpainting algorithms based on the TUM-image inpainting database. The experimental results show that the proposed diffusion model is efficient and achieves superior performance. Moreover, we also demonstrate that the proposed method has a texture preserving property, that makes it stand out from previous PDE based methods.
Original languageEnglish
Title of host publicationPattern Recognition
Subtitle of host publication37th German Conference, GCPR 2015, Aachen, Germany, October 7-10, 2015, Proceedings
PublisherSpringer International Publishing AG
Pages356-367
Volume9358
ISBN (Electronic)978-3-319-24947-6
ISBN (Print)978-3-319-24946-9
DOIs
Publication statusAccepted/In press - 2015

    Fingerprint

Fields of Expertise

  • Information, Communication & Computing

Cite this

Yu, W., Heber, S., & Pock, T. (Accepted/In press). Learning Reaction-Diffusion Models for Image Inpainting. In Pattern Recognition: 37th German Conference, GCPR 2015, Aachen, Germany, October 7-10, 2015, Proceedings (Vol. 9358, pp. 356-367). Springer International Publishing AG . https://doi.org/10.1007/978-3-319-24947-6_29