paper-with-me

홈 › Papers

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

2018-07-22 · Chih-Chung Hsu, Chia-Wen Lin, Weng-Tai Su, Gene Cheung

Despite generative adversarial networks (GANs) can hallucinate photo-realistic high-resolution (HR) faces from low-resolution (LR) faces, they cannot guarantee preserving the identities of hallucinated HR faces, making the HR faces poorly recognizable. To address this problem, we propose a Siamese GAN (SiGAN) to reconstruct HR faces that visually resemble their corresponding identities. On top of a Siamese network, the proposed SiGAN consists of a pair of two identical generators and one discriminator. We incorporate reconstruction error and identity label information in the loss function of SiGAN in a pairwise manner. By iteratively optimizing the loss functions of the generator pair and discriminator of SiGAN, we cannot only achieve photo-realistic face reconstruction, but also ensures the reconstructed information is useful for identity recognition. Experimental results demonstrate that SiGAN significantly outperforms existing face hallucination GANs in objective face verification performance, while achieving photo-realistic reconstruction. Moreover, for input LR faces from unknown identities who are not included in training, SiGAN can still do a good job.

📄 PDF Abstract BibTeX arXiv:1807.08370

Code (1)

jesse1029/SiGAN tf

Tasks

Face HallucinationFace ReconstructionFace VerificationGenerative Adversarial NetworkHallucination

Similar Papers 제목 키워드 기반

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

2021-04-11 · Binyi Su, Zhong Zhou, Haiyong Chen, Xiaochun Cao

Solar cell electroluminescence (EL) defect segmentation is an interesting and challenging topic. Many methods have been proposed for EL defect detection, but these methods are still unsatisfactory due to the diversity of…

Defect DetectionGenerative Adversarial NetworkImage GenerationSegmentation

Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net

2022-07-01 · Findings (NAACL) 2022 7 · Xin Sheng, Linli Xu, Yinlong Xu, Deqiang Jiang 외

We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text. Different from previous generative adversarial net based method…

Abstractive Text SummarizationText Summarization

Generate Identity-Preserving Faces by Generative Adversarial Networks

2017-06-10 · Zhigang Li, Yupin Luo

Generating identity-preserving faces aims to generate various face images keeping the same identity given a target face image. Although considerable generative models have been developed in recent years, it is still chal…

k-Same-Siamese-GAN: k-Same Algorithm with Generative Adversarial Network for Facial Image De-identification with Hyperparameter Tuning and Mixed Precision Training

2019-03-27 · Yi-Lun Pan, Min-Jhih Huang, Kuo-Teng Ding, Ja-Ling Wu 외

For a data holder, such as a hospital or a government entity, who has a privately held collection of personal data, in which the revealing and/or processing of the personal identifiable data is restricted and prohibited …

De-identificationGenerative Adversarial Network

Semantically Decomposing the Latent Spaces of Generative Adversarial Networks

2017-05-22 · ICLR 2018 1 · Chris Donahue, Zachary C. Lipton, Akshay Balsubramani, Julian McAuley

We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity p…

Face VerificationImage Generation