Parallel Region-Based Deep Residual Networks for Face Hallucination

Lü, Tao; Hao, Xiaohui; Zhang, Yanduo; Liu, Kai; Xiong, Zixiang

doi:10.1109/access.2019.2923023

Cited by 10 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As far as we know, the MFSR method is a new topic in the field of computers, and there is no relevant open source code. Therefore, we compare the latest single-input face SR methods and multi-input generic image SR methods, including LCGE [38], SRCNN [20], EDGAN [22], TDAE [21], PRDRN [23], PASSRent [26], and SRNTT [39] methods. For a fair comparison, we retrain and test the comparison methods using the same face datasets.…”

Section: Resultsmentioning

confidence: 99%

“…Yang et al [22] proposed a face method based on Generative Adversarial Networks (GAN) to restore reasonable visual output HR face images. Recently, Lu et al [23] proposed a regionbased deep residual network for face hallucination, which utilizes face images to learn further fine structural prior information. Although SFSR provides an end-to-end effective solution for supervised learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-View Texture Learning for Face Super-Resolution

Wang

Lü

Feng

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

In recent years, single face image super-resolution (SR) using deep neural networks have been well developed. However, most of the face images captured by the camera in a real scene are from different views of the same person, and the existing traditional multi-frame image SR requires alignment between images. Due to multi-view face images contain texture information from different views, which can be used as effective prior information, how to use this prior information from multi-views to reconstruct frontal face images is challenging. In order to effectively solve the above problems, we propose a novel face SR network based on multi-view face images, which focus on obtaining more texture information from multi-view face images to help the reconstruction of frontal face images. And in this network, we also propose a texture attention mechanism to transfer high-precision texture compensation information to the frontal face image to obtain better visual effects. We conduct subjective and objective evaluations, and the experimental results show the great potential of using multi-view face images SR. The comparison with other state-of-the-art deep learning SR methods proves that the proposed method has excellent performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-View Texture Learning for Face Super-Resolution

Wang

Lü

Feng

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to AAN, SRDSI decomposes the face into a basic face with low-frequency and enhance face with high-frequency through PCA, and recovers the basic face with very deep convolutional networks (VDSR) [79], repairs enhance face with sparse representation, and finally fuses the recovered enhance face and the basic face. Thereafter, many patch-based methods occurs, including [80,193,111,110,123], all of which crop face images into several patches and train models for recovering corresponding patches.…”

Section: General Face Super-resolution Methodsmentioning

confidence: 99%

Deep Learning-based Face Super-Resolution: A Survey

Jiang¹,

Wang²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Face super-resolution, also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) one or a sequence of face images to generate the corresponding high-resolution (HR) face images, is a domain-specific image super-resolution problem. Recently, face super-resolution has received considerable attention, and witnessed dazzling advances with deep learning techniques. To date, few summaries of the studies on the deep learning-based face super-resolution are available. In this survey, we present a comprehensive review of deep learning techniques in face super-resolution in a systematic manner. First, we summarize the problem formulation of face super-resolution. Second, we compare the differences between generic image super-resolution and face super-resolution. Third, datasets and performance metrics commonly used in facial hallucination are presented. Fourth, we roughly categorize existing methods according to the utilization of face-specific information. In

show abstract

“…Similarly, structure information was considered in the deep learning framework. For example, Lu et al developed a parallel region based deep residual network (PRDRN) to predict the missing detailed information for accurate face hallucination [32]. Usually, deep learning based methods demand a large training dataset, intensive computation and memory resources [29].…”

Section: Introductionmentioning

confidence: 99%

Face hallucination based on cluster consistent dictionary learning

Lam

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Face hallucination is a super-resolution technique specially designed to reconstruct highresolution faces from low-resolution faces. Most state-of-the-art algorithms leverage position-patch prior knowledge of human faces to better super-resolve face images. However, most of them assume the training face dataset is sufficiently large, well cropped or aligned. This paper, proposes a novel example-based face hallucination method, based on cluster consistent dictionary learning with the assumption that human faces have similar facial structures. In this method, the paired face image patches are firstly labelled as face areas including eyes, nose, mouth and other parts, as well as non-face areas without requiring the training face images cropped and aligned. Then, the training patches are clustered according their labels and textures. The cluster consistent dictionary is learned to represent the low-resolution patches and the high-resolution patches. Finally, the high-resolution patches of the input low-resolution face image can be efficiently generated by using the adjusted anchored neighbourhood regression. As utilizing the labelled facial parts prior knowledge, the proposed method represents more details in the reconstruction. Experimental results demonstrate that the authors' algorithm outperforms many state-of-the-art techniques for face hallucination under different datasets.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Parallel Region-Based Deep Residual Networks for Face Hallucination

Cited by 10 publications

References 49 publications

Multi-View Texture Learning for Face Super-Resolution

Multi-View Texture Learning for Face Super-Resolution

Deep Learning-based Face Super-Resolution: A Survey

Face hallucination based on cluster consistent dictionary learning

Contact Info

Product

Resources

About