3D Reconstruction of Human Faces: a Laplacian Approach

• Grant number: 23/15751-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2024
• End date: December 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computational Mathematics
• Principal Investigator: João Do Espirito Santo Batista Neto
• Grantee: João Pedro Viguini Tolentino Taufner Correa
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 19/07316-0 - Singularity theory and its applications to differential geometry, differential equations and computer vision, AP.TEM

Abstract

One of the current challenges in the field of image processing and computer vision is the mapping of robust features between two-dimensional and three-dimensional spaces. This process can be simplified by reducing the amount of information when representing curves from points (called robust features or important points), so that they can be reconstructed using these with minimal error. In the 3D context, we can use anchor points from which to reconstruct the mesh, the resolution of which increases as the number of points in the sample grows. This study is part of one of the lines of action of the FAPESP thematic project 2019/07316-0, which aims to reconstruct human faces from reduced domain information