SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination

Hsu, Chih–Chung; Lin, Chia‐Wen; Su, Weng-Tai; Cheung, Gene

doi:10.1109/tip.2019.2924554

Cited by 77 publications

(30 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To achieve high fidelity of SR performance, the proposed 24.28 0.7170 GLFSR [17] 24.19 0.7136 SiGAN [18] 24.17 0.7255 FSRGAN [3] 24.41 0.7250 EIPNet [19] 25.08 0.7429 Ours 25.07 0.7519…”

Section: Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Progressive Face Super-Resolution with Non-Parametric Facial Prior Enhancement

Kim

Jung

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

The main challenge of face super-resolution is to overcome facial distortions in an upscaling process. Recent works have utilized facial priors such as facial landmarks and component maps to generate a precise super-resolved image. However, the facial priors are estimated from the ground-truth and deep neural networks. Thus, recent works based on the facial priors are not only limited to specific datasets including the groundtruth, but also need sub-networks to extract facial priors. To solve these problems, we propose a progressive face superresolution network with non-parametric facial prior enhancement, called as NPFNet, which extracts and highlights facial components without any tricks, such as the ground-truth and deep neural networks. The self-enhancement module facilitates our network to fully utilize facial distinct features to enhance super-resolved images with a parameter-free operation. Extensive experiments on CelebA and VGGFace2 demonstrate that the proposed method outperforms state-of-the-art face super-resolution methods in terms of visual quality and quantitative measurements.

show abstract

“…To achieve high fidelity of SR performance, the proposed 24.28 0.7170 GLFSR [17] 24.19 0.7136 SiGAN [18] 24.17 0.7255 FSRGAN [3] 24.41 0.7250 EIPNet [19] 25.08 0.7429 Ours 25.07 0.7519…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Kim et al [4] 22.65 0.6699 IDN [1] 24.26 0.6969 GLFSR [17] 24.06 0.6887 SiGAN [18] 24.29 0.7103 FSRGAN [3] 24.30 0.7017 EIPNet [19] 24.56 0.7066 Ours 26.48 0.7577…”

Section: Vggface2mentioning

confidence: 99%

Progressive Face Super-Resolution with Non-Parametric Facial Prior Enhancement

Kim

Jung

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…A similar argument can also be made in the case of deep learning-based face super-resolution algorithms. In spite of their great ability to add visually pleasing details to LR images, these algorithms often neglect how much beneficial the added information is for the task of recognizing the identity of the face [34]. Most of the loss functions that have been considered in the literature are designed to minimize the mean square error (MSE) between the HR image and its corresponding reconstructed one, which, although can sometimes achieve high MSE-oriented quality metrics, in most cases produce blurry and over-smoothed results [35].…”

Section: A Motivation and Contributionmentioning

confidence: 99%

Identity-Preserving Pose-Robust Face Hallucination Through Face Subspace Prior

Abbasi¹,

Rahmati²

2021

Preprint

View full text Add to dashboard Cite

Over the past few decades, numerous attempts have been made to address the problem of recovering a high-resolution (HR) facial image from its corresponding low-resolution (LR) counterpart, a task commonly referred to as face hallucination. Despite the impressive performance achieved by position-patch and deep learning-based methods, most of these techniques are still unable to recover identity-specific features of faces. The former group of algorithms often produces blurry and oversmoothed outputs particularly in the presence of higher levels of degradation, whereas the latter generates faces which sometimes by no means resemble the individuals in the input images. In this paper, a novel face super-resolution approach will be introduced, in which the hallucinated face is forced to lie in a subspace spanned by the available training faces. Therefore, in contrast to the majority of existing face hallucination techniques and thanks to this <i>face subspace prior</i>, the reconstruction is performed in favor of recovering person-specific facial features, rather than merely increasing image quantitative scores. Furthermore, inspired by recent advances in the area of 3D face reconstruction, an efficient 3D dictionary alignment scheme is also presented, through which the algorithm becomes capable of dealing with low-resolution faces taken in uncontrolled conditions. In extensive experiments carried out on several well-known face datasets, the proposed algorithm shows remarkable performance by generating detailed and close to ground truth results which outperform the state-of-the-art face hallucination algorithms by significant margins both in quantitative and qualitative evaluations.

show abstract

“…To evaluate the reconstruction performance of the GCFSRnet at the upscale factor of 4 and 8, we compared with state-ofthe-art SR methods, including SRGAN [22], SRResNet [22], VDSR [15], DBPN [33], FSRNet [29], SiGAN [34], ATMFN [35]. SRGAN, SRResNet, and VDSR only provide 4× upscale models, while DBPN, FSRNet, SiGAN, and ATMFN provide 4× and 8× upscale models.…”

Section: Comparison With State-of-the-artmentioning

confidence: 99%

Guided Cascaded Super-Resolution Network for Face Image

Cao

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The image super-resolution algorithm can overcome the imaging system's hardware limitation and obtain higher resolution and clearer images. Existing super-resolution methods based on convolutional neural networks(CNN) can learn the mapping relationship between high-resolution(HR) and low-resolution(LR) images. However, when the reconstruction target is a face image, the reconstruction results often have problems that the face area is too smooth and lacks details. We propose a guided cascaded face super-resolution network, called guided cascaded super-resolution network (GCFSRnet). GCFSRnet takes the LR image and a high-quality guided image as inputs, and it consists of a pose deformation module and a super-resolution network. Firstly, the pose deformation module converts the guide image's posture into the same as the low-resolution face image based on 3D fitting and 3D morphable model (3DMM). Then, the LR image and the deformed guide image are used as input of the super-resolution network. The super-resolution networks are formed by a cascade of two layers of networks, which extract different features. During the reconstruction process, the guide image can provide real facial details and help generate subtle facial textures. The cascade structure of a super-resolution network can gradually extract features and restore different levels of image details. The experimental results on the CASIA Web Face and CelebA datasets show that the proposed method can generate facial images with clear outlines and rich details, which are superior to other state-of-the-art methods such as SRResNet, SRGAN, VDSR, DBPN, etc.

show abstract

SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination

Cited by 77 publications

References 33 publications

Progressive Face Super-Resolution with Non-Parametric Facial Prior Enhancement

Progressive Face Super-Resolution with Non-Parametric Facial Prior Enhancement

Identity-Preserving Pose-Robust Face Hallucination Through Face Subspace Prior

Guided Cascaded Super-Resolution Network for Face Image

Contact Info

Product

Resources

About