Related papers: SRTransGAN: Image Super-Resolution using Transform…

Recent convolutional object detectors exploit multi-scale feature representations added with top-down pathway in order to detect objects at different scales and learn stronger semantic feature responses. In general, during the top-down…

While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled framework to simultaneously mitigate two fundamental issues in…

In recent years, with the rapid development of artificial intelligence, image generation based on deep learning has dramatically advanced. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, since…

Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images. However, they often struggle in learning complex underlying modalities in a given dataset, resulting in poor-quality generated…

Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets. The efficiency of traditional clustering algorithms heavily depends on the distance functions used and the…

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…

We show that pre-trained Generative Adversarial Networks (GANs) such as StyleGAN and BigGAN can be used as a latent bank to improve the performance of image super-resolution. While most existing perceptual-oriented approaches attempt to…

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the…

The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated with training with conventional 3D representations, such as…

Generative models, such as GANs, learn an explicit low-dimensional representation of a particular class of images, and so they may be used as natural image priors for solving inverse problems such as image restoration and compressive…

In medical imaging, image synthesis is the estimation process of one image (sequence, modality) from another image (sequence, modality). Since images with different modalities provide diverse biomarkers and capture various features,…

CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in…

The problem of generating textual descriptions for the visual data has gained research attention in the recent years. In contrast to that the problem of generating visual data from textual descriptions is still very challenging, because it…

Style synthesis attracts great interests recently, while few works focus on its dual problem "style separation". In this paper, we propose the Style Separation and Synthesis Generative Adversarial Network (S3-GAN) to simultaneously…

Advances in face rotation, along with other face-based generative tasks, are more frequent as we advance further in topics of deep learning. Even as impressive milestones are achieved in synthesizing faces, the importance of preserving…

Spatial resolution of medical images can be improved using super-resolution methods. Real Enhanced Super Resolution Generative Adversarial Network (Real-ESRGAN) is one of the recent effective approaches utilized to produce higher resolution…

The paper proposes a method to effectively fuse multi-exposure inputs and generate high-quality high dynamic range (HDR) images with unpaired datasets. Deep learning-based HDR image generation methods rely heavily on paired datasets. The…

Image-to-image translation is considered a new frontier in the field of medical image analysis, with numerous potential applications. However, a large portion of recent approaches offers individualized solutions based on specialized…

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by…

The advancement of high-performance computing has enabled the generation of large direct numerical simulation (DNS) datasets of turbulent flows, driving the need for efficient compression/decompression techniques that reduce storage demands…