Highly corrupted image inpainting through hypoelliptic diffusion

Abstract : We present a new image inpainting algorithm, the Averaging and Hypoelliptic Evolution (AHE) algorithm, inspired by the one presented in [1] and based upon a (semi-discrete) variation of the Citti--Petitot--Sarti model of the primary visual cortex V1. In particular, we focus on reconstructing highly corrupted images (i.e. where more than the 80% of the image is missing). [1] U. Boscain, R. A. Chertovskih, J. P. Gauthier, and A. O. Remizov, Hypoelliptic diffusion and human vision: a semidiscrete new twist, SIAM J. Imaging Sci., vol. 7, no. 2, pp. 669--695, 2014.
Document type :
Journal articles
Complete list of metadatas

Cited literature [41 references]  Display  Hide  Download

https://hal.inria.fr/hal-01139521
Contributor : Dario Prandi <>
Submitted on : Friday, June 8, 2018 - 1:10:33 PM
Last modification on : Friday, October 18, 2019 - 11:38:05 AM
Long-term archiving on : Sunday, September 9, 2018 - 4:27:15 PM

File

1502.07331.pdf
Files produced by the author(s)

Identifiers

Citation

Ugo Boscain, Roman Chertovskih, Jean-Paul Gauthier, Dario Prandi, Alexey Remizov. Highly corrupted image inpainting through hypoelliptic diffusion. Journal of Mathematical Imaging and Vision, Springer Verlag, 2018, pp.1-15. ⟨10.1007/s10851-018-0810-4⟩. ⟨hal-01139521v2⟩

Share

Metrics

Record views

520

Files downloads

470