Filters








4,997 Hits in 7.1 sec

Guided Cascaded Super-Resolution Network for Face Image

Lin Cao, Jiape Liu, Kangning Du, Yanan Guo, Tao Wang
2020 IEEE Access  
OVERVIEW OF GCFSRNET In this work, we propose a novel guided cascaded face super-resolution network called GCFSRnet.  ...  Therefore, we introduce a Guided Cascaded Face Super-Resolution network called GCFSRnet. The proposed GCF-SRnet consists of a pose deformation module and a superresolution network.  ... 
doi:10.1109/access.2020.3025972 fatcat:nghrwibck5bsngps5jfr7lgvd4

Deep Cascaded Bi-Network for Face Hallucination [chapter]

Shizhan Zhu, Sifei Liu, Chen Change Loy, Xiaoou Tang
2016 Lecture Notes in Computer Science  
We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD 1 ).  ...  In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details.  ...  Cascaded prediction. The cascaded framework is privileged both for image super-resolution (SR) [15, 25] and facial landmark detection [27, 2, 3, 22, 28, 23, 29, 30] . For image SR, Wang et al.  ... 
doi:10.1007/978-3-319-46454-1_37 fatcat:4n5mkl2p6bg2hbzhqrwfj35kqy

Deep Cascaded Bi-Network for Face Hallucination [article]

Shizhan Zhu, Sifei Liu, Chen Change Loy, Xiaoou Tang
2016 arXiv   pre-print
We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD).  ...  In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details.  ...  Deep convolutional neural networks have demonstrated state-of-the-art results for image super resolution [14, 15, 17, 18] .  ... 
arXiv:1607.05046v1 fatcat:v66wzdvwujgrrbvlnykupm4vxa

Deep Learning-based Face Super-Resolution: A Survey [article]

Junjun Jiang, Chenyang Wang, Xianming Liu, Jiayi Ma
2021 arXiv   pre-print
Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) face images to generate high-resolution (HR) face images, is a domain-specific  ...  image super-resolution problem.  ...  INTRODUCTION Face super-resolution (FSR), a domain-specific image super-resolution problem, refers to the technique of recovering high-resolution (HR) face images from low-resolution (LR) face images.  ... 
arXiv:2101.03749v2 fatcat:q56d2mpn4rfyzmi5fo36d2ecja

Deep Learning-based Face Super-resolution: A Survey

Junjun Jiang, Chenyang Wang, Xianming Liu, Jiayi Ma
2023 ACM Computing Surveys  
Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) face images to generate high-resolution face images, is a domain-specific  ...  image super-resolution problem.  ...  INTRODUCTION Face super-resolution (FSR), a domain-specific image super-resolution problem, refers to the technique of recovering high-resolution (HR) face images from low-resolution (LR) face images.  ... 
doi:10.1145/3485132 fatcat:gxaod3eqs5gkbmtow3k4jrrpvy

Face hallucination using cascaded super-resolution and identity priors

Klemen Grm, Walter J. Scheirer, Vitomir Struc
2019 IEEE Transactions on Image Processing  
The model consists of two main parts: i) a cascaded super-resolution network that upscales the low-resolution facial images, and ii) an ensemble of face recognition models that act as identity priors for  ...  The proposed C-SRIP model (Cascaded Super Resolution with Identity Priors) is able to upscale (tiny) low-resolution images captured in unconstrained conditions and produce visually convincing results for  ...  Our SR network is guided by face-recognition models that ignore non-face regions. • Significant occlusion. In images 14(a) and 14(d), the face is partially occluded by a foreground object.  ... 
doi:10.1109/tip.2019.2945835 pmid:31613762 fatcat:35qwxawe4ba4bajtbum2jvgu7q

Face hallucination using cascaded super-resolution and identity priors [article]

Klemen Grm and Simon Dobrišek and Walter J. Scheirer and Vitomir Štruc
2019 arXiv   pre-print
The model consists of two main parts: i) a cascaded super-resolution network that upscales the low-resolution images, and ii) an ensemble of face recognition models that act as identity priors for the  ...  super-resolution network during training.  ...  The model consists of two main parts: i) a cascaded super-resolution network that upscales the low-resolution images, and ii) an ensemble of face recognition models that act as identity priors for the  ... 
arXiv:1805.10938v2 fatcat:sd46zusrdjconctjpwnkoqaeeq

Facial image super-resolution guided by adaptive geometric features

Zhenfeng Fan, Xiyuan Hu, Chen Chen, Xiaolian Wang, Silong Peng
2020 EURASIP Journal on Wireless Communications and Networking  
Current state-of-the-art super-resolution (SR) methods commonly adopt the convolutional neural networks to learn a non-linear complex mapping between paired LR and HR images.  ...  As a special case of general images, the face has limited geometric variations, which we believe that the relevant depth map can be learned and used to guide the face SR task.  ...  Face super-resolution, also known as face hallucination for heavily blurred images, aims at recovering a high-resolution (HR) facial image from a low-resolution (LR) one.  ... 
doi:10.1186/s13638-020-01760-y fatcat:7rhc4uvtwvadtcextzapvqb6re

Face Super-Resolution Guided by 3D Facial Priors [article]

Xiaobin Hu, Wenqi Ren, John LaMaster, Xiaochun Cao, Xiaoming Li, Zechao Li, Bjoern Menze, Wei Liu
2020 arXiv   pre-print
., intensity similarity, 3D facial structure, and identity content) for the super-resolution problem.  ...  State-of-the-art face super-resolution methods employ deep convolutional neural networks to learn a mapping between low- and high- resolution facial patterns by exploring local appearance knowledge.  ...  [21] proposed a Feature-Guided Super-Resolution Generative Adversarial Network (FG-SRGAN) for unpaired image super-resolution.  ... 
arXiv:2007.09454v1 fatcat:gyxdruuling7bdaoetiwjkigei

PAGER: Progressive Attribute-Guided Extendable Robust Image Generation [article]

Zohreh Azizi, C.-C. Jay Kuo
2022 arXiv   pre-print
The core generator learns the distribution of low-resolution images and performs unconditional image generation. The resolution enhancer increases image resolution via conditional generation.  ...  Unlike most generative models in the literature, our method does not utilize neural networks to analyze the underlying source distribution and synthesize images.  ...  The authors acknowledge the Center for Advanced Research Computing (CARC) at the University of Southern California for providing computing resources that have contributed to the research results reported  ... 
arXiv:2206.00162v2 fatcat:4xo5jfcahzgkjl3etcmsbzkyhy

Attention-Aware Face Hallucination via Deep Reinforcement Learning

Qingxing Cao, Liang Lin, Yukai Shi, Xiaodan Liang, Guanbin Li
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Face hallucination is a domain-specific super-resolution problem with the goal to generate high-resolution (HR) faces from low-resolution (LR) input images.  ...  ., face hallucination result for the whole image) can thus be exploited and updated by the local enhancement network on the selected region.  ...  We employ the cascaded convolution network architecture similar to general image super-resolution methods [3, 13] .  ... 
doi:10.1109/cvpr.2017.180 dblp:conf/cvpr/CaoLSLL17 fatcat:7o47dujtaff6ldvwzdgjzolbbu

A Study on the Performance of Unconstrained Very Low Resolution Face Recognition: Analyzing Current Trends and New Research Directions

Luis S. Luevano, Leonardo Chang, Heydi Mendez-Vazquez, Yoanna Martinez-Diaz, Miguel Gonzalez-Mendoza
2021 IEEE Access  
In this survey, we study the seminal and novel methods to tackle the very low resolution face recognition problem and provide an in-depth analysis of their design, effectiveness, and efficiency for a real-time  ...  Furthermore, we analyze the advantage of employing deep learning convolutional neural networks, while presenting future research directions for effective deep learning network design in this context.  ...  The Cascaded Super-Resolution with Identity Prior (C-SRIP) [30] consists of three sequential super resolution modules for a cascaded training methodology.  ... 
doi:10.1109/access.2021.3080712 fatcat:hkzki3uw4jgn5gygqrntzlzkti

Joint Residual Pyramid for Depth Map Super-Resolution [chapter]

Yi Xiao, Xiang Cao, Yan Zheng, Xianyi Zhu
2018 Lecture Notes in Computer Science  
The network takes residual network as the main frame and adopts the cascaded pyramid structure for phased upsampling.  ...  The network directly uses the low-resolution depth image as the initial input of the network and the subpixel convolution layers is used for upsampling. It reduces the computational complexity.  ...  ESPCN) Hui [2] CNN (multi-scale guided convolutional network MSG-Net) [15] (very deep convolutional for super resolution VDSR) Lai [18] (Laplacian pyramid super-resolution network LapSRN) 3) 金字塔密集残差网络  ... 
doi:10.1007/978-3-319-97304-3_61 fatcat:cnfclce4gngg5dxcwbnvpp5epa

Exemplar Guided Face Image Super-Resolution Without Facial Landmarks

Berk Dogan, Shuhang Gu, Radu Timofte
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we propose a convolutional neural network (CNN)-based solution, namely GWAInet, which applies super-resolution (SR) by a factor 8× on face images guided by another unconstrained HR face  ...  Therefore, for super-resolving a given very lowresolution (LR) face image of a person it is very likely to find another HR face image of the same person which can be used to guide the process.  ...  Introduction Face image super-resolution or face hallucination aims at reconstructing details / high-frequencies in low-resolution (LR) face images.  ... 
doi:10.1109/cvprw.2019.00232 dblp:conf/cvpr/DoganGT19 fatcat:p73wcwsgcjgb3lbbxv23qzgqlu

Self-Enhanced Convolutional Network for Facial Video Hallucination [article]

Chaowei Fang, Guanbin Li, Xiaoguang Han, Yizhou Yu
2019 arXiv   pre-print
As a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks.  ...  Taking advantage of high inter-frame dependency in videos, we propose a self-enhanced convolutional network for facial video hallucination.  ...  Video super resolution, as an extension of image super resolution, attracts more attentions for its practicality but being more challenging.  ... 
arXiv:1911.11136v1 fatcat:xavmtdckufa6ngargrf4lspv5a
« Previous Showing results 1 — 15 out of 4,997 results