With the development of 3D vision techniques, in particular neural network based methods, the 3D neural avatar representation has gained growing interest both in the academia and in the industry. Such digital representations have been applied to movie, video game, fashion and virtual reality environments to enrich user experiences. In terms of 3D representation and reconstruction, classic methods rely on heavy setups and costly computation processes while neural networks open up the possibility to handle this problem from partial observations thanks to tolerance to insufficient information. In particular, neural networks achieve promising results for reconstruction tasks with a high speed inference process. However, at the time of the thesi...
This work introduces a neural network for estimating the detailed 3D structure of the foreground hum...
In this thesis, we address the challenges of 3D scene reconstruction and completion from sparse and ...
The past decade was marked by significant progress in the field of artificial intelligence and stati...
With the development of 3D vision techniques, in particular neural network based methods, the 3D neu...
In this manuscript, we propose data-driven methods to generate realistic 3D human motion. Although d...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
Dans cette thèse, nous proposons des méthodes basées sur les données pour générer des mouvements hum...
The 3D virtual representations of dressed humans appear in movies, video games and since recently, V...
International audienceWe address the problem of inferring a human shape from partial observations, s...
Les représentations virtuelles 3D de l'humain habillé apparaissent dans les films, les jeux vidéo, et...
In the broad field of computer vision, Three-Dimensional (3D) Human shape and body understanding has...
International audienceWe study the problem of reconstructing the template-aligned mesh for human bod...
The goal of this thesis is to develop deep learning approaches to model and analyse 3D shapes. Progr...
International audienceWe address the problem of completing partial human shape observations as obtai...
Data-driven models of the 3D face are a promising direction for capturing the subtle complexities of...
This work introduces a neural network for estimating the detailed 3D structure of the foreground hum...
In this thesis, we address the challenges of 3D scene reconstruction and completion from sparse and ...
The past decade was marked by significant progress in the field of artificial intelligence and stati...
With the development of 3D vision techniques, in particular neural network based methods, the 3D neu...
In this manuscript, we propose data-driven methods to generate realistic 3D human motion. Although d...
The focus of visual content is often people. Automatic analysis of people from visual data is theref...
Dans cette thèse, nous proposons des méthodes basées sur les données pour générer des mouvements hum...
The 3D virtual representations of dressed humans appear in movies, video games and since recently, V...
International audienceWe address the problem of inferring a human shape from partial observations, s...
Les représentations virtuelles 3D de l'humain habillé apparaissent dans les films, les jeux vidéo, et...
In the broad field of computer vision, Three-Dimensional (3D) Human shape and body understanding has...
International audienceWe study the problem of reconstructing the template-aligned mesh for human bod...
The goal of this thesis is to develop deep learning approaches to model and analyse 3D shapes. Progr...
International audienceWe address the problem of completing partial human shape observations as obtai...
Data-driven models of the 3D face are a promising direction for capturing the subtle complexities of...
This work introduces a neural network for estimating the detailed 3D structure of the foreground hum...
In this thesis, we address the challenges of 3D scene reconstruction and completion from sparse and ...
The past decade was marked by significant progress in the field of artificial intelligence and stati...