Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination
Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination
Junjun Jiang, Yi Yu, Jinhui Hu, Suhua Tang, Jiayi Ma
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 771-778.
https://doi.org/10.24963/ijcai.2018/107
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training set. They mainly focus on modeling image prior through either model-based optimization or discriminative inference learning. However, when the input LR face is tiny, the learned prior knowledge is no longer effective and their performance will drop sharply. To solve this problem, in this paper we propose a general face hallucination method that can integrate model-based optimization and discriminative inference. In particular, to exploit the model based prior, the Deep Convolutional Neural Networks (CNN) denoiser prior is plugged into the super-resolution optimization model with the aid of image-adaptive Laplacian regularization. Additionally, we further develop a high-frequency details compensation method by dividing the face image to facial components and performing face hallucination in a multi-layer neighbor embedding manner. Experiments demonstrate that the proposed method can achieve promising super-resolution results for tiny input LR faces.
Keywords:
Computer Vision: Statistical Methods and Machine Learning
Computer Vision: Biometrics, Face and Gesture Recognition
Machine Learning Applications: Other Applications
Computer Vision: Computer Vision