Generate novel views for partially occluded objects using a data-driven approach

• Forschungsstelle: INNOSUISSE
• Projektnummer: 15599.1 PFES-ES
• Projekttitel Englisch: Generate novel views for partially occluded objects using a data-driven approach

Kurzbeschreibung (Deutsch)

Generate novel views for partially occluded objects using a data-driven approach

Kurzbeschreibung (Englisch)

Generate novel views for partially occluded objects using a data-driven approach

Abstract (Deutsch)

In this CTI project, ETH Zurich and LiberoVision AG will investigate and design novel methods to generate high quality free view-point point video with the focus on a data-driven approach. We propose to design a new approach handling occlusions by introducing novel ways for geometry- and texture completion. The data-driven solution will also allow improving the resolution of player textures. This will open new markets in sports analysis.

Abstract (Englisch)

In this CTI project, ETH Zurich and LiberoVision AG will investigate and design novel methods to generate high quality free view-point point video with the focus on a data-driven approach. We propose to design a new approach handling occlusions by introducing novel ways for geometry- and texture completion. The data-driven solution will also allow improving the resolution of player textures. This will open new markets in sports analysis.