Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

Segmentation-Reconstruction-Guided Facial Image De-occlusion

Abstract : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Xiangnan YIN Connect in order to contact the contributor
Submitted on : Tuesday, January 11, 2022 - 10:09:29 AM
Last modification on : Wednesday, November 2, 2022 - 4:17:03 PM
Long-term archiving on: : Tuesday, April 12, 2022 - 6:40:29 PM


Files produced by the author(s)


  • HAL Id : hal-03482857, version 1
  • ARXIV : 2112.08022


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



Record views


Files downloads