Features Guided Face Super-Resolution via Hybrid Model of Deep Learning and Random Forests

Face hallucination or super-resolution is a practical application of general image super-resolution which has been recently studied by many researchers. The challenge of good face hallucination comes from a variety of poses, illuminations, facial expressions, and other degradations. In many proposed methods, researchers resolve it by using a generative neural network to reduce the perceptual loss so we can generate a photo-realistic image. The problem is that researchers usually overlook the fidelity of the super-resolved image which could affect further facial image processing. Meanwhile, many CNN based approaches cascade multiple networks to extract facial prior information to improve super-resolution quality. Because of the end-to-end design, the details are missing for investigation. In this paper, we combine new techniques in convolutional neural network and random forests to a Hierarchical CNN based Random Forests (HCRF) approach for face super-resolution in a coarse-to-fine manner. In the proposed approach, we focus on a general approach that can handle facial images with various conditions without pre-processing. To the best of our knowledge, this is the first paper that combines the advantages of deep learning with random forests for face super-resolution. To achieve superior performance, we propose two novel CNN models for coarse facial image super-resolution and segmentation and then apply new random forests to target on local facial features refinement making use of the segmentation results. Extensive benchmark experiments on subjective and objective evaluation show that HCRF can achieve comparable speed and competitive performance compared with state-of-the-art super-resolution approaches for very low-resolution images.

Automated summary

This paper introduces a new approach, Hierarchical CNN based Random Forests (HCRF), for face super-resolution by combining convolutional neural networks and random forests. The proposed method is capable of handling facial images under various conditions without preprocessing. By incorporating the advantages of deep learning with random forests, two novel CNN models are proposed for coarse facial image super-resolution and segmentation, along with new random forests for refining local facial features based on the segmentation results. Extensive benchmark experiments demonstrate that HCRF achieves comparable speed and competitive performance compared to state-of-the-art super-resolution approaches for very low-resolution images.