Learning Pixel-Perfect 3D Vision and Generative Modeling

Informazioni relative al progetto

PIPE

ID dell’accordo di sovvenzione: 866435

DOI

10.3030/866435

Progetto chiuso

Data della firma CE 7 Febbraio 2020

Data di avvio 1 Settembre 2020

Data di completamento 31 Agosto 2025

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 858 013,00

Contributo UE

€ 1 858 013,00

Coordinato da

AALTO KORKEAKOULUSAATIO SR
Finland

Periodic Reporting for period 4 - PIPE (Learning Pixel-Perfect 3D Vision and Generative Modeling)

Periodo di rendicontazione: 2025-03-01 al 2025-08-31

Sintesi del contesto e degli obiettivi generali del progetto

PIPE seeks to advance computers' capability to reason about the physical world by looking at nothing but pictures. Moreover, PIPE seeks to enable this reasoning to stand on solid, physically meaningful quantities. Concretely, PIPE studies both the problem of understanding what shapes, materials, lights, objects, etc., appear in pictures of real-world scenes, as well as the problem of generative modeling, i.e. learning "a recipe" for the world.

Solutions to these fundamental problems in computer vision, computer graphics, and machine learning are relevant for a large number of applications from computer graphics, augmented and virtual reality to robotics; clearly, truly understanding the messy complexity of the real world must be necessary, e.g. for reliable, safe autonomous machines to emerge.

Lavoro eseguito dall’inizio del progetto fino alla fine del periodo coperto dalla relazione e principali risultati finora ottenuti

PIPE seeks to advance the state of the art on three axes: (1) understanding the shapes in the world; (2) understanding the visual complexity of the surface materials in the world; and (3) learning generative computational recipes for things in the world. The most significant achievement since the beginning of the project is a result in the final direction that combines intuitive, controllable computational components with modern machine learning techniques. This enables photorealistic generative modeling in terms of physically meaningful concepts and quantities while requiring no human supervision.

Progressi oltre lo stato dell’arte e potenziale impatto previsto (incluso l’impatto socioeconomico e le implicazioni sociali più ampie del progetto fino ad ora)

PIPE is expected to provide breakthrough results in how well computer vision and generative algorithms can understand our three-dimensional world.

Overview of the approach in "A hybrid generator architecture for controllable face synthesis"