Deep Learning Face Hallucination via Attributes Transfer and Enhancement
Lists
Only you see this
Abstract
Face hallucination technique aims to generate high-resolution (HR) face images from low-resolution (LR) inputs. Even though existing face hallucination methods have achieved great performance on the global region evaluation, most of them cannot reasonably restore local attributes, especially when ultra-resolving tiny LR face image (16 × 16 pixels) to its larger version (8× upscaling factor). In this paper, we propose a novel attribute-guided face transfer and enhancement network for face hallucination. Specifically, we first construct a face transfer network, which upsamples LR face images to HR feature maps, and then fuses facial attributes and the upsampled features to generate HR face images with rational attributes. Finally, a face enhancement network is developed based on generative adversarial network (GAN) to improve visual quality by exploiting a composite loss that combines image color, texture and content. Extensive experiments demonstrate that our method achieves superior face hallucination results and outperforms the state-of-the-art.
BibTeX
@inproceedings{li2019deep,
author = {Mengyan Li and Yuechuan Sun and Zhaoyu Zhang and Haonian Xie and Jun Yu},
title = {{Deep Learning Face Hallucination via Attributes Transfer and Enhancement}},
booktitle = {ICME},
year = {2019},
url = {https://openreview.net/forum?id=H3V-frEZ--q},
}Loading related content...