Cortical-inspired image reconstruction via sub-Riemannian geometry and hypoelliptic diffusion

DOI10.1051/PROC/201864037zbMATH Open1486.68227arXiv1801.03800OpenAlexW3125453379WikidataQ115334254 ScholiaQ115334254MaRDI QIDQ4615500FDOQ4615500

Alexey O. Remizov, Ugo Boscain, R. A. Chertovskih, Jean-Paul Gauthier, Dario Prandi

Publication date: 29 January 2019

Published in: ESAIM: Proceedings and Surveys (Search for Journal in Brave)

Abstract: In this paper we review several algorithms for image inpainting based on the hypoelliptic diffusion naturally associated with a mathematical model of the primary visual cortex. In particular, we present one algorithm that does not exploit the information of where the image is corrupted, and others that do it. While the first algorithm is able to reconstruct only images that our visual system is still capable of recognize, we show that those of the second type completely transcend such limitation providing reconstructions at the state-of-the-art in image inpainting. This can be interpreted as a validation of the fact that our visual cortex actually encodes the first type of algorithm.

Full work available at URL: https://arxiv.org/abs/1801.03800

Mathematics Subject Classification ID

Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Computing methodologies for image processing (68U10)

Cites Work

• Majoration en temps petit de la densité d'une diffusion dégénérée
• Minoration en temps petit de la densité d'une diffusion dégénérée. (Lower estimate for small times of the density of a degenerate diffusion)
• Filling-in by joint interpolation of vector fields and gray levels
• Euler's Elastica and Curvature-Based Inpainting
• Title not available (Why is that?)
• Minimal surfaces in the roto-translation group with applications to a neuro-biological image completion model
• Maxwell strata in sub-Riemannian problem on the group of motions of a plane
• Fast anisotropic smoothing of multi-valued images using curvature-preserving PDE's
• The visual cortex is a contact bundle
• Anthropomorphic image reconstruction via hypoelliptic diffusion
• The explicit solutions of linear left-invariant second order stochastic evolution equations on the 2D Euclidean motion group
• Left-invariant parabolic evolutions on $SE(2)$ and contour enhancement via invertible orientation scores Part I: Linear left-invariant diffusion equations on $SE(2)$
• Title not available (Why is that?)
• Association fields via cuspless sub-Riemannian geodesics in SE(2)
• Sub-Riemannian mean curvature flow for image processing
• A parallel algorithm and software for image inpainting via sub-Riemannian minimizers on the group of rototranslations
• Hypoelliptic diffusion and human vision: a semidiscrete new twist
• Left-invariant parabolic evolutions on $SE(2)$ and contour enhancement via invertible orientation scores Part II: Nonlinear left-invariant diffusions on invertible orientation scores
• Curve cuspless reconstructionviasub-Riemannian geometry
• Geometrically Guided Exemplar-Based Inpainting
• Convex relaxation of a class of vertex penalizing functionals
• Highly corrupted image inpainting through hypoelliptic diffusion
• Image compression with anisotropic diffusion
• A Semidiscrete Version of the Citti-Petitot-Sarti Model as a Plausible Model for Anthropomorphic Image Reconstruction and Pattern Recognition
• A finite difference scheme on a non commutative group

Cited In (2)

• Cortically based optimal transport
• DIP-VBTV: A Color Image Restoration Model Combining a Deep Image Prior and a Vector Bundle Total Variation

This page was built for publication: Cortical-inspired image reconstruction via sub-Riemannian geometry and hypoelliptic diffusion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4615500)