Related papers: GLEAN: Generative Latent Bank for Large-Factor Ima…

Generative adversarial networks (GANs) are a class of unsupervised machine learning algorithms that can produce realistic images from randomly-sampled vectors in a multi-dimensional space. Until recently, it was not possible to generate…

In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where…

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we…

Image super-resolution is one of the important computer vision techniques aiming to reconstruct high-resolution images from corresponding low-resolution ones. Most recently, deep learning-based approaches have been demonstrated for image…

Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking images of faces, scenery and even medical images. Unfortunately, they usually require large training datasets, which are often scarce in…

Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to an input real image. This editing property emerges from the disentangled nature…

Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities. Specifically, BigGANs a class-conditional Generative Adversarial Networks trained on ImageNet---achieved excellent,…

Several research groups have shown that Generative Adversarial Networks (GANs) can generate photo-realistic images in recent years. Using the GANs, a map is created between a latent code and a photo-realistic image. This process can also be…

Generative Adversarial Networks (GANs) have made great success in synthesizing high-quality images. However, how to steer the generation process of a well-trained GAN model and customize the output image is much less explored. It has been…

Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial…

Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the…

As many other machine learning driven medical image analysis tasks, skin image analysis suffers from a chronic lack of labeled data and skewed class distributions, which poses problems for the training of robust and well-generalizing…

Generative Adversarial Networks (GANs) with style-based generators (e.g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

GAN-based image restoration inverts the generative process to repair images corrupted by known degradations. Existing unsupervised methods must be carefully tuned for each task and degradation level. In this work, we make StyleGAN image…

Recently, the power of unconditional image synthesis has significantly advanced through the use of Generative Adversarial Networks (GANs). The task of inverting an image into its corresponding latent code of the trained GAN is of utmost…

Generative Adversarial Networks (GANs) have emerged as a significant player in generative modeling by mapping lower-dimensional random noise to higher-dimensional spaces. These networks have been used to generate high-resolution images and…

In the past decades, the excessive use of the last-generation GAN (Generative Adversarial Networks) models in computer vision has enabled the creation of artificial face images that are visually indistinguishable from genuine ones. These…

Despite the breakthroughs in quality of image enhancement, an end-to-end solution for simultaneous recovery of the finer texture details and sharpness for degraded images with low resolution is still unsolved. Some existing approaches focus…

Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by…