Learning Pixel-Perfect 3D Vision and Generative Modeling

Información del proyecto

PIPE

Identificador del acuerdo de subvención: 866435

DOI

10.3030/866435

Proyecto cerrado

Fecha de la firma de la CE 7 Febrero 2020

Fecha de inicio 1 Septiembre 2020

Fecha de finalización 31 Agosto 2025

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 858 013,00

Aportación de la UE

€ 1 858 013,00

Coordinado por

AALTO KORKEAKOULUSAATIO SR
Finland

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

Período documentado: 2025-03-01 hasta 2025-08-31

Resumen del contexto y de los objetivos generales del proyecto

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.

Trabajo realizado desde el comienzo del proyecto hasta el final del período abarcado por el informe y los principales resultados hasta la fecha

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.

Avances que van más allá del estado de la técnica e impacto potencial esperado (incluida la repercusión socioeconómica y las implicaciones sociales más amplias del proyecto hasta la fecha)

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"