Face Hallucination Using Cascaded Super-Resolution and Identity Priors

Grm, Klemen; Scheirer, Walter J.; Štruc, Vitomir

doi:10.1109/tip.2019.2945835

Cited by 88 publications

(58 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the aforementioned methods perform well for natural image deblurring, they often do not perform satisfactorily on domain-specific images such as face images. Therefore, several studies have proposed estimating various types of prior facial knowledge such as the face alignment [4], face sketches [6], reference faces [2], [31], 3D face models [3], and face segmentation maps [7], [8]. The reference priorbased methods [2], [31] extract useful information to restore the face image from a sharp face similar to a degraded face image.…”

Section: B Face Image Deblurringmentioning

confidence: 99%

Progressive Semantic Face Deblurring

2020

View full text Add to dashboard Cite

Previous face deblurring methods have utilized semantic segmentation maps as prior knowledge. Most of these methods generated the segmentation map from a blurred facial image, and restore it using the map in a sequential manner. However, the accuracy of the segmentation affects the restoration performance. Generally, it is difficult to obtain an accurate segmentation map from a blurred image. Instead of sequential methods, we propose an efficient method that learns the flows of facial component restoration without performing segmentation. To this end, we propose a multi-semantic progressive learning (MSPL) framework that progressively restores the entire face image starting from the facial components such as the skin, followed by the hair, and the inner parts (eyes, nose, and mouth). Furthermore, we propose a discriminator that observes the reconstruction-flow of the generator. In addition, we present new test datasets to facilitate the comparison of face deblurring methods. Various experiments demonstrate that the proposed MSPL framework achieves higher performance in facial image deblurring compared to the existing methods, both qualitatively and quantitatively. Our code, trained model and data are available at https://github.com/dolphin0104/MSPL-GAN. INDEX TERMS Facial image deblurring, semantic mask, progressive learning, generative adversarial network, deep learning

show abstract

Section: B Face Image Deblurringmentioning

confidence: 99%

Progressive Semantic Face Deblurring

2020

View full text Add to dashboard Cite

show abstract

“…Using the presented setup, we study the effect of dataset bias using five recent FH (or super-resolution) models, i.e. : the Ultra Resolving Discriminative Generative Network (URDGN, [44]), the Deep Laplacian Super-Resolution Network (LapSRN, [21]), the Super-Resolution Residual Network (SRResNet, [22]), the Cascading Residual Network (CARN, [1]), and the Cascading Super Resolution Network with Identity Priors (C-SRIP, [11]). The selected models differ in the network architecture and training objective, but are all considered to produce state-of-the-art hallucination results as shown in Fig.…”

Section: Face Hallucination (Fh) Modelsmentioning

confidence: 99%

“…Face hallucination (FH) refers to the task of recovering high-resolution (HR) facial images from corresponding low-resolution (LR) inputs [2,6,11]. Solutions to this task have applications in face-oriented vision problems, such as face editing and alignment, 3D reconstruction or face attribute estimation [3,6,19,23,24,25,31,43] and are used to mitigate performance degradations caused by input images of insufficient resolution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Face Hallucination Revisited: An Exploratory Study on Dataset Bias

Grm

Pernuš

Cluzel

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

View full text Add to dashboard Cite

Contemporary face hallucination (FH) models exhibit considerable ability to reconstruct high-resolution (HR) details from low-resolution (LR) face images. This ability is commonly learned from examples of corresponding HR-LR image pairs, created by artificially down-sampling the HR ground truth data. This down-sampling (or degradation) procedure not only defines the characteristics of the LR training data, but also determines the type of image degradations the learned FH models are eventually able to handle. If the image characteristics encountered with realworld LR images differ from the ones seen during training, FH models are still expected to perform well, but in practice may not produce the desired results. In this paper we study this problem and explore the bias introduced into FH models by the characteristics of the training data. We systematically analyze the generalization capabilities of several FH models in various scenarios, where the image the degradation function does not match the training setup and conduct experiments with synthetically downgraded as well as real-life low-quality images. We make several interesting findings that provide insight into existing problems with FH models and point to future research directions.

show abstract

“…After introducing the pool layer, the network depth reaches five layers, and the network structure with deeper layers is more conducive to the learning of image data. At the same time, the number of parameters can be reduced by pooling layer [13] [14].…”

Section: Pooled Layermentioning

confidence: 99%

Human Face Super-Resolution Based on Hybrid Algorithm

Xia¹,

Yang²,

Li³

et al. 2018

AMI

View full text Add to dashboard Cite

Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new algorithm model. The classical convolutional neural network is improved, the convolution kernel size is adjusted, and the parameters are reduced; the pooling layer is added to reduce the dimension. Reduced computational complexity, increased learning rate, and reduced training time. The iterative back-projection algorithm is combined with the convolutional neural network to create a new algorithm model. The experimental results show that compared with the traditional facial illusion method, the proposed method can obtain better performance.

show abstract

Face Hallucination Using Cascaded Super-Resolution and Identity Priors

Cited by 88 publications

References 70 publications

Progressive Semantic Face Deblurring

Progressive Semantic Face Deblurring

Face Hallucination Revisited: An Exploratory Study on Dataset Bias

Human Face Super-Resolution Based on Hybrid Algorithm

Contact Info

Product

Resources

About