Generative Adversarial Networks (GANs) have witnessed increasing attention due to their abilities to model complex visual data distributions, which allow them to generate and translate realistic images. While realistic \textit{video generation} is the natural sequel, it is substantially more challenging w.r.t. complexity and computation, associated to the simultaneous modeling of appearance, as well as motion. Specifically, in inferring and modeling the distribution of human videos, generative models face three main challenges: (a) generating uncertain motion and retaining of human appearance, (b) modeling spatio-temporal consistency, as well as (c) understanding of latent representation. In this thesis, we propose three novel approaches to...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
We propose a new method for realistic human motion transfer using a generative adversarial network (...
Generative Adversarial Networks (GANs) have been witnessed tremendous successes in broad Computer Vi...
Generative Adversarial Networks (GANs) have witnessed increasing attention due to their abilities to...
Les réseaux antagonistes génératifs (GAN) ont suscité une attention croissante en raison de leurs ca...
Generation of realistic high-resolution videos of human subjects is a challenging and important task...
International audienceCreating realistic human videos entails the challenge of being able to simulta...
Generative models, such as Auto-Encoders, Generative Adversarial Networks, Generative Flows, and Dif...
Learning to edit facial images and videos is one of the most popular tasks in both academia and indu...
The past years have seen a great progress of deep generative models, including Generative Adversaria...
Generative adversarial models (GANs) continue to produce advances in terms of the visual quality of ...
Expressing ideas in our minds which are inevitably visual into words had been a necessity. Lack of t...
Generative models have shown impressive results in generating synthetic images. However, video synth...
Learning to represent and generate videos from unlabeled data is a very challenging problem. To gene...
This thesis focuses on the synthesis of motion capture data with statistical models. Motion synthesi...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
We propose a new method for realistic human motion transfer using a generative adversarial network (...
Generative Adversarial Networks (GANs) have been witnessed tremendous successes in broad Computer Vi...
Generative Adversarial Networks (GANs) have witnessed increasing attention due to their abilities to...
Les réseaux antagonistes génératifs (GAN) ont suscité une attention croissante en raison de leurs ca...
Generation of realistic high-resolution videos of human subjects is a challenging and important task...
International audienceCreating realistic human videos entails the challenge of being able to simulta...
Generative models, such as Auto-Encoders, Generative Adversarial Networks, Generative Flows, and Dif...
Learning to edit facial images and videos is one of the most popular tasks in both academia and indu...
The past years have seen a great progress of deep generative models, including Generative Adversaria...
Generative adversarial models (GANs) continue to produce advances in terms of the visual quality of ...
Expressing ideas in our minds which are inevitably visual into words had been a necessity. Lack of t...
Generative models have shown impressive results in generating synthetic images. However, video synth...
Learning to represent and generate videos from unlabeled data is a very challenging problem. To gene...
This thesis focuses on the synthesis of motion capture data with statistical models. Motion synthesi...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
We propose a new method for realistic human motion transfer using a generative adversarial network (...
Generative Adversarial Networks (GANs) have been witnessed tremendous successes in broad Computer Vi...