logo
v2.11.0 (6271)

Cours scientifiques - CSC_53433_EP : Modèles créatifs et génératifs en infographie

Domaine > Informatique.

Descriptif

This course presents the techniques for content creation in 3D Computer Graphics, from 3D shapes to animated landscapes and character motion, with a focus on their link with AI. We first introduce user-centered Creative AI (also called Expressive modeling methods), i.e. smart 3D models - either based on knowledge or trained from examples, designed to help users create/generate the 3D shapes their have in mind, and their organisation into complex, static or animated scenes. Second, we study the use of AI in Character Animation, from early motion planning and control methods to deep reinforcement learning solutions for generating the gaits of physically-based characters. These methods result into 3D agents able to navigate alone or within crowds, and to interact with their environment. The lab sessions are held on Unity, based on C#.
 

24 heures en présentiel

30 heures de travail personnel estimé pour l’étudiant.

Diplôme(s) concerné(s)

Parcours de rattachement

Pour les étudiants du diplôme MScT-Artificial Intelligence and Advanced Visual Computing

Bases en informatique graphique, animation par ordinateur et apprentissage automatique.

Format des notes

Numérique sur 20

Littérale/grade réduit

Pour les étudiants du diplôme MScT-Artificial Intelligence and Advanced Visual Computing

Vos modalités d'acquisition :

Ce cours est évalué via deux exercices, réalisés en binome ou en trinome:

  • Une étude bibliographique (comparaison d'articles) suivie d'un exposé
  • Un projet réalisé en Unity, présenté lors d'une mini soutenance

La note finale est la moyenne des deux notes.

Le rattrapage est autorisé (Note de rattrapage conservée)
    L'UE est acquise si Note finale >= 10
    • Crédits ECTS acquis : 2 ECTS

    Programme détaillé

    This course consists of two parts, each consisting of 6 hours of lectures and 6 hours of practical work:

    1. User-Centered Creative AI, i.e., how interactive content creation can be enhanced using intelligent graphical models that integrate knowledge to enable intuitive gesture-based creation. As we will demonstrate, this "expressive modeling" methodology can be applied to a variety of scenarios, from the design of individual products to be manufactured to the creation of complete, animated virtual worlds.

    2. Autonomous characters have been referred to for decades as the "AIs" of virtual worlds. We will first describe the main methods for animating character models, detailing each layer—from the brain to the skeletal movement, including skin and hair—that contributes to bringing a virtual creature to life. The final lectures will focus on autonomous character navigation, where movement planning and control will be developed for both individual and group characters.

    Keywords
    Computer graphics, computer-aided design, autonomous characters

    Teaching methods
    Magistrate course (3 hours per week) + labs (3 hours per week)

    Mots clés

    Informatique graphique, systèmes d'aide à la création, personnages autonomes

    Méthodes pédagogiques

    Cours magistrat (3h par semaine) + TP (3h par semaine)

    Support pédagogique multimédia

    Oui

    Veuillez patienter