Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by
Transformative Discriminative Autoencoders
Abstract
Most of the conventional face hallucination methods assume the input image is sufficiently large and aligned, and
all require the input image to be noise-free. Their performance degrades drastically if the input image is tiny, unaligned, and contaminated by noise.
In this paper, we introduce a novel transformative discriminative autoencoder to 8× super-resolve unaligned
noisy and tiny (16×16) low-resolution face images. In contrast to encoder-decoder based autoencoders, our method
uses decoder-encoder-decoder networks. We first employ
a transformative discriminative decoder network to upsample and denoise simultaneously. Then we use a transformative encoder network to project the intermediate HR faces
to aligned and noise-free LR faces. Finally, we use the second decoder to generate hallucinated HR images. Our extensive evaluations on a very large face dataset show that
our method achieves superior hallucination results and outperforms the state-of-the-art by a large margin of 1.82 dB
PSNR.