Style attention based global-local aware GAN for personalized facial caricature generation

Article Computer Science, Information Systems

Recurrent Generative Adversarial Network for Face Completion

Qiang Wang et al.

Summary: This paper proposes a Recurrent Generative Adversarial Network (RGAN) for face completion, which leverages multi-level features and advanced representations from multiple perspectives to restore spatial information and details in semantic texture content.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Information Systems

AttentionFGAN: Infrared and Visible Image Fusion Using Attention-Based Generative Adversarial Networks

Jing Li et al.

Summary: In this paper, a method named AttentionFGAN is proposed to fuse infrared and visible images by integrating multi-scale attention mechanism into Generative Adversarial Networks (GAN). The generator and discriminator both apply attention mechanism to emphasize the focus on typical regions of source images during fusion. Ablation experiments demonstrate the effectiveness of the method, and extensive qualitative and quantitative experiments on three public datasets show the advantages of AttentionFGAN compared to other state-of-the-art methods.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Information Systems

Supervised Pixel-Wise GAN for Face Super-Resolution

Menglei Zhang et al.

Summary: The paper introduces a supervised pixel-wise Generative Adversarial Network (SPGAN) that can upscale low-resolution face images to larger versions with multiple scaling factors. By utilizing face features and identity prior, SPGAN enhances face recognition performance by focusing on texture details. Extensive experiments show that SPGAN produces more photo-realistic super-resolution images and better face recognition accuracy compared to state-of-the-art methods.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Artificial Intelligence