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

Chih Chung Hsu, Chia Wen Lin, Weng Tai Su, Gene Cheung

研究成果: Article同行評審

66 引文 斯高帕斯(Scopus)


Though generative adversarial networks (GANs) can hallucinate high-quality high-resolution (HR) faces from low-resolution (LR) faces, they cannot ensure identity preservation during face hallucination, making the HR faces difficult to recognize. 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 the discriminator of SiGAN, we not only achieve visually-pleasing face reconstruction but also ensure that 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 promising visual-quality reconstruction. Moreover, for input LR faces with unseen identities that are not part of the training dataset, SiGAN can still achieve reasonable performance.

頁(從 - 到)6225-6236
期刊IEEE Transactions on Image Processing
出版狀態Published - 2019 12月

All Science Journal Classification (ASJC) codes

  • 軟體
  • 電腦繪圖與電腦輔助設計


深入研究「SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination」主題。共同形成了獨特的指紋。