Segmentation-Reconstruction-Guided Facial Image De-occlusion - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Segmentation-Reconstruction-Guided Facial Image De-occlusion

Di Huang
  • Fonction : Auteur
Zehua Fu
  • Fonction : Auteur
Yunhong Wang
  • Fonction : Auteur
Liming Chen

Résumé

Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. Although much effort has been devoted to removing occlusions from face images, the varying shapes and textures of occlusions still challenge the robustness of current methods. As a result, current methods either rely on manual occlusion masks or only apply to specific occlusions. This paper proposes a novel face de-occlusion model based on face segmentation and 3D face reconstruction, which automatically removes all kinds of face occlusions with even blurred boundaries,e.g., hairs. The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module. With the face prior and the occlusion mask predicted by the first two, respectively, the image generation module can faithfully recover the missing facial textures. To supervise the training, we further build a large occlusion dataset, with both manually labeled and synthetic occlusions. Qualitative and quantitative results demonstrate the effectiveness and robustness of the proposed method.
Fichier principal
Vignette du fichier
Yin_Huang_Fu_2021.pdf (8.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03482857 , version 1 (11-01-2022)

Identifiants

Citer

Xiangnan Yin, Di Huang, Zehua Fu, Yunhong Wang, Liming Chen. Segmentation-Reconstruction-Guided Facial Image De-occlusion. 2022. ⟨hal-03482857⟩
44 Consultations
85 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More