Multi-scale attention network for image inpainting

J Qin, H Bai, Y Zhao - Computer Vision and Image Understanding, 2021 - Elsevier
Recently, deep learning based inpainting methods have shown promising performance, in
which some multi-scale networks are introduced to characterize image content in both …

GCM-Net: Towards effective global context modeling for image inpainting

H Zheng, Z Zhang, Y Wang, Z Zhang, M Xu… - Proceedings of the 29th …, 2021 - dl.acm.org
Deep learning based inpainting methods have obtained promising performance for image
restoration, however current image inpainting methods still tend to produce unreasonable …

Visual illusions via neural dynamics: Wilson–Cowan-type models and the efficient representation principle

M Bertalmío, L Calatroni, V Franceschi… - Journal of …, 2020 - journals.physiology.org
We reproduce suprathreshold perception phenomena, specifically visual illusions, by Wilson–
Cowan (WC)-type models of neuronal dynamics. Our findings show that the ability to …

[HTML][HTML] A Cortical-Inspired Contour Completion Model Based on Contour Orientation and Thickness

I Galyaev, A Mashtakov - Journal of Imaging, 2024 - mdpi.com
An extended four-dimensional version of the traditional Petitot–Citti–Sarti model on contour
completion in the visual cortex is examined. The neural configuration space is considered as …

Cortical-inspired Wilson–Cowan-type equations for orientation-dependent contrast perception modelling

M Bertalmio, L Calatroni, V Franceschi… - Journal of Mathematical …, 2021 - Springer
We consider the evolution model proposed in Bertalmío (Front Comput Neurosci 8: 71,
2014), Bertalmío et al.(IEEE Trans Image Process 16 (4): 1058–1072, 2007) to describe …

[图书][B] A semidiscrete version of the Citti-Petitot-Sarti model as a plausible model for anthropomorphic image reconstruction and pattern recognition

D Prandi, JP Gauthier - 2018 - books.google.com
This book proposes a semi-discrete version of the theory of Petitot and Citti-Sarti, leading to
a left-invariant structure over the group SE (2, N), restricted to a finite number of rotations …

Total variation and mean curvature PDEs on the homogeneous space of positions and orientations

BMN Smets, J Portegies, E St-Onge, R Duits - Journal of Mathematical …, 2021 - Springer
Two key ideas have greatly improved techniques for image enhancement and denoising:
the lifting of image data to multi-orientation distributions and the application of nonlinear …

Multi-frequency image completion via a biologically-inspired sub-Riemannian model with frequency and phase

E Baspinar - Journal of Imaging, 2021 - mdpi.com
We present a novel cortically-inspired image completion algorithm. It uses five-dimensional
sub-Riemannian cortical geometry, modeling the orientation, spatial frequency and phase …

Face inpainting network for large missing regions based on weighted facial similarity

J Qin, H Bai, Y Zhao - Neurocomputing, 2020 - Elsevier
Recently, deep learning has made great achievements in the field of image inpainting,
especially filling the large missing regions based on generative adversarial net (GAN) …

Sigma Flows for Image and Data Labeling and Learning Structured Prediction

J Cassel, B Boll, S Petra, P Albers… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper introduces the sigma flow model for the prediction of structured labelings of data
observed on Riemannian manifolds, including Euclidean image domains as special case …