Thumbnail

Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation

Fu, Changqing; Cohen, Laurent D. (2021), Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation, Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), 2021-05, on line, FRANCE

Voir/Ouvrir
Type
Communication / Conférence
Date
2021
Titre du colloque
Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)
Date du colloque
2021-05
Ville du colloque
on line
Pays du colloque
FRANCE
Métadonnées
Afficher la notice complète
Auteur(s)
Fu, Changqing
Cohen, Laurent D.
Résumé (EN)
A novel two-stage approach is proposed for image manipulation and generation. User-interactive image deformation is performed through editing of contours. This is performed in the latent edge space with both color and gradient information. The output of editing is then fed into a multi-scale representation of the image to recover quality output. The model is flexible in terms of transferability and training efficiency.
Mots-clés
Machine Learning; Image Generation; Generative Adversarial Network; Image deformation; Contour Editing