Related papers: Multi-level Latent Space Structuring for Generativ…

Generative models dealing with modeling a~joint data distribution are generally either autoencoder or GAN based. Both have their pros and cons, generating blurry images or being unstable in training or prone to mode collapse phenomenon,…

Many important problems in science and engineering, such as drug design, involve optimizing an expensive black-box objective function over a complex, high-dimensional, and structured input space. Although machine learning techniques have…

Unpaired image-to-image translation using Generative Adversarial Networks (GAN) is successful in converting images among multiple domains. Moreover, recent studies have shown a way to diversify the outputs of the generator. However, since…

Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the…

Deep generative models are known to be able to model arbitrary probability distributions. Among these, a recent deep generative model, dubbed sliceGAN, proposed a new way of using the generative adversarial network (GAN) to capture the…

In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors $w^+\in\mathcal{W}^+$ specific to each image. Therefore, $\mathcal{W}^+$ space is often used for image inversion and…

Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis…

We present a novel discriminator for GANs that improves realness and diversity of generated samples by learning a structured hypersphere embedding space using spherical circles. The proposed discriminator learns to populate realistic…

Although deep learning has achieved impressive advances in transient stability assessment of power systems, the insufficient and imbalanced samples still trap the training effect of the data-driven methods. This paper proposes a…

High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the…

StyleGAN is known to produce high-fidelity images, while also offering unprecedented semantic editing. However, these fascinating abilities have been demonstrated only on a limited set of datasets, which are usually structurally aligned and…

This paper investigates an open research task of reconstructing and generating 3D point clouds. Most existing works of 3D generative models directly take the Gaussian prior as input for the decoder to generate 3D point clouds, which fail to…

Quantization is a widely adopted technique for deep neural networks to reduce the memory and computational resources required. However, when quantized, most models would need a suitable calibration process to keep their performance intact,…

StyleGAN family is one of the most popular Generative Adversarial Networks (GANs) for unconditional generation. Despite its impressive performance, its high demand on storage and computation impedes their deployment on resource-constrained…

While recent research has progressively overcome the low-resolution constraint of one-shot face video re-enactment with the help of StyleGAN's high-fidelity portrait generation, these approaches rely on at least one of the following:…

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, high-dimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution,…

The research topic of sketch-to-portrait generation has witnessed a boost of progress with deep learning techniques. The recently proposed StyleGAN architectures achieve state-of-the-art generation ability but the original StyleGAN is not…

Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups and may lead to unfair attention with respect to various facial attributes such as gender and origin. The main reason…

This paper describes a new technique for finding disentangled semantic directions in the latent space of StyleGAN. Our method identifies meaningful orthogonal subspaces that allow editing of one human face attribute, while minimizing…

This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine…