Descrizione del progetto
Insegnare ai computer a vedere
La visione artificiale è un’area dell’intelligenza artificiale (IA). L’obiettivo della visione artificiale è quello di dotare le macchine di una comprensione visiva del loro ambiente, consentendo in ultima analisi ai computer di identificare gli oggetti nelle immagini e nei video proprio come fanno gli esseri umani. Gran parte dei recenti progressi nel campo della visione artificiale si basa su tecniche di apprendimento automatico che apprendono le rappresentazioni visive da grandi insiemi di dati contenenti annotazioni umane. Tuttavia, etichettare i dati per l’addestramento dei modelli di apprendimento approfondito è costoso e i simulatori foto-realistici esistenti non forniscono la varietà e la fedeltà necessarie. Il progetto LEGO-3D, finanziato dall’UE, affronterà questo problema sviluppando modelli probabilistici in grado di sintetizzare scene 3D insieme a proiezioni 2D foto-realistiche da punti di vista arbitrari e con il pieno controllo degli elementi della scena. Verranno messi a punto algoritmi per la scomposizione automatica di scene reali e sintetiche in rappresentazioni 3D latenti che catturano la geometria, il materiale, la luce e il movimento.
Obiettivo
Recently, the field of computer vision has witnessed a major transformation away from expert designed shallow models towards more generic deep representation learning. However, collecting labeled data for training deep models is costly and existing simulators with artist-designed scenes do not provide the required variety and fidelity. Project LEGO-3D will tackle this problem by developing probabilistic models capable of synthesizing 3D scenes jointly with photo-realistic 2D projections from arbitrary viewpoints and with full control over the scene elements. Our key insight is that data augmentation, while hard in 2D, becomes considerably easier in 3D as physical properties such as viewpoint invariances and occlusion relationships are captured by construction. Thus, our goal is to learn the entire 3D-to-2D simulation pipeline. In particular, we will focus on the following problems:
(A) We will devise algorithms for automatic decomposition of real and synthetic scenes into latent 3D primitive representations capturing geometry, material, light and motion.
(B) We will develop novel probabilistic generative models which are able to synthesize large-scale 3D environments based on the primitives extracted in project (A). In particular, we will develop unconditional, conditioned and spatio-temporal scene generation networks.
(C) We will combine differentiable and neural rendering techniques with deep learning based image synthesis, yielding high-fidelity 2D renderings of the 3D representations generated in project (B) while capturing ambiguities and uncertainties.
Project LEGO-3D will significantly impact a large number of application areas. Examples include vision systems which require access to large amounts of annotated data, safety-critical applications such as autonomous cars that rely on efficient ways for training and validation, as well as the entertainment industry which seeks to automate the creation and manipulation of 3D content.
Campo scientifico
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencesmathematicspure mathematicsgeometry
Parole chiave
Programma(i)
Argomento(i)
Meccanismo di finanziamento
ERC-STG - Starting GrantIstituzione ospitante
72074 Tuebingen
Germania