Hallucinating very low-Resolution unaligned and noisy face images by transformative discriminative autoencoders
-
Altmetric Citations
Description
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 8X super-resolve unaligned noisy and tiny (16X16) low-resolution face images. In contrast to encoder-decoder based autoencoders, our method uses...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2017 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/204436 |
Source: | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
DOI: | 10.1109/CVPR.2017.570 |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Yu_Hallucinating_very_2017.pdf | 1.27 MB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator