Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation

Résumé

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.
Fichier principal
Vignette du fichier
SSVM21FINALarticle.pdf (5.21 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03424127 , version 1 (10-11-2021)

Identifiants

  • HAL Id : hal-03424127 , version 1

Citer

Changqing Fu, Laurent D. Cohen. Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation. Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), May 2021, Virtual, France. ⟨hal-03424127⟩
51 Consultations
64 Téléchargements

Partager

Gmail Facebook X LinkedIn More