Radiometric confidence criterion for patch-based inpainting

Abstract : Diminished Reality (DR) consists in virtually removing objects from a captured scene, thus requiring a coherent filling of the areas originally hidden behind these objects. Indoor DR applications often exploit the planar geometry of the scene to apply an inpainting process on a perspectively undistorted view of the plane. In this paper we propose to integrate a novel, physic-based criterion into classical state-of-the-art inpainting algorithms in order to take into account the variations in image resolution of the undistorted view. The proposed inpainting process selects the patches and avoids the propagation of low-resolution data, i.e. patches corresponding to parts of the plane that are far from the camera or seen under an very skew angle. We illustrate the improvements of DR results on synthetic and real images.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01895288
Contributor : Simone Gasparini <>
Submitted on : Monday, October 15, 2018 - 8:55:29 AM
Last modification on : Friday, April 12, 2019 - 4:23:08 PM
Document(s) archivé(s) le : Wednesday, January 16, 2019 - 1:24:12 PM

File

radiometric-confidence-criteri...
Files produced by the author(s)

Identifiers

Collections

Citation

Julien Fayer, Geraldine Morin, Simone Gasparini, Maxime Daisy, Benjamin Coudrin. Radiometric confidence criterion for patch-based inpainting. Proceedings of the International Conference on Pattern Recognition (ICPR), Aug 2018, Beijing, China. ⟨10.1109/ICPR.2018.8545350⟩. ⟨hal-01895288⟩

Share

Metrics

Record views

48

Files downloads

46