Learning Oracle Attention for High-Fidelity Face Completion
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7677-7686
Abstract
High-fidelity face completion is a challenging task due to the rich and subtle facial textures involved. What makes it more complicated is the correlations between different facial components, for example, the symmetry in texture and structure between both eyes. While recent works adopted the attention mechanism to learn the contextual relations among elements of the face, they have largely overlooked the disastrous impacts of inaccurate attention scores; in addition, they fail to pay sufficient attention to key facial components, the completion results of which largely determine the authenticity of a face image. Accordingly, in this paper, we design a comprehensive framework for face completion based on the U-Net structure. Specifically, we propose a dual spatial attention module to efficiently learn the correlations between facial textures at multiple scales; moreover, we provide an oracle supervision signal to the attention module to ensure that the obtained attention scores are reasonable. Furthermore, we take the location of the facial components as prior knowledge and impose a multi-discriminator on these regions, with which the fidelity of facial components is significantly promoted. Extensive experiments on two high-resolution face datasets including CelebA-HQ and Flickr-Faces-HQ demonstrate that the proposed approach outperforms state-of-the-art methods by large margins.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Globally and locally consistent image completionACM Transactions on Graphics, 2017
- Semantic Image Inpainting with Deep Generative Models2017
- Generative Face Completion2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Context Encoders: Feature Learning by Inpainting2016
- One millisecond face alignment with an ensemble of regression trees2014
- Robust exemplar-based inpainting algorithm using region segmentationIEEE Transactions on Consumer Electronics, 2012
- Statistics of Patch Offsets for Image Completion2012
- PatchMatch2009
- Region Filling and Object Removal by Exemplar-Based Image InpaintingIEEE Transactions on Image Processing, 2004