Descripción del proyecto
Nuevas técnicas de análisis de imágenes para hacer avanzar la modelización del mundo tridimensional
Los algoritmos de visión por ordenador encierran un gran potencial para la modelización y la comprensión del mundo visual. El objetivo del proyecto 3D Reloaded, financiado por el Consejo Europeo de Investigación, es crear nuevas técnicas de análisis de imágenes centrándose en la reconstrucción y el análisis de la estructura tridimensional del mundo. La investigación se orientará a tres ámbitos: el desarrollo de algoritmos de reconstrucción tridimensional (3D) en tiempo real utilizando cámaras de color estándares y cámaras de color y profundidad (RGB-D); la creación de algoritmos (casi) óptimos para el análisis de formas 3D, y el diseño de priores de forma (modelos que describen la geometría de los objetos) para la reconstrucción 3D, ya sean aprendidos a partir de muestras de formas o adquiridos durante el proceso. Los avances en la reconstrucción y el análisis geométricos tendrán importantes implicaciones más allá del campo de la visión por ordenador.
Objetivo
Despite their amazing success, we believe that computer vision algorithms have only scratched the surface of what can be done in terms of modeling and understanding our world from images. We believe that novel image analysis techniques will be a major enabler and driving force behind next-generation technologies, enhancing everyday life and opening up radically new possibilities. And we believe that the key to achieving this is to develop algorithms for reconstructing and analyzing the 3D structure of our world.
In this project, we will focus on three lines of research:
A) We will develop algorithms for 3D reconstruction from standard color cameras and from RGB-D cameras. In particular, we will promote real-time-capable direct and dense methods. In contrast to the classical two-stage approach of sparse feature-point based motion estimation and subsequent dense reconstruction, these methods optimally exploit all color information to jointly estimate dense geometry and camera motion.
B) We will develop algorithms for 3D shape analysis, including rigid and non-rigid matching, decomposition and interpretation of 3D shapes. We will focus on algorithms which are optimal or near-optimal. One of the major computational challenges lies in generalizing existing 2D shape analysis techniques to shapes in 3D and 4D (temporal evolutions of 3D shape).
C) We will develop shape priors for 3D reconstruction. These can be learned from sample shapes or acquired during the reconstruction process. For example, when reconstructing a larger office algorithms may exploit the geometric self-similarity of the scene, storing a model of a chair and its multiple instances only once rather than multiple times.
Advancing the state of the art in geometric reconstruction and geometric analysis will have a profound impact well beyond computer vision. We strongly believe that we have the necessary competence to pursue this project. Preliminary results have been well received by the community.
Ámbito científico
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorsoptical sensors
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- natural sciencesmathematicspure mathematicsgeometry
- natural sciencescomputer and information sciencessoftwaresoftware applicationssimulation software
Programa(s)
Régimen de financiación
ERC-COG - Consolidator GrantInstitución de acogida
80333 Muenchen
Alemania