Acquiring 3D Human Model from Uncalibrated Monocular Image Sequence

E. Peng and L. Li (Australia)

Keywords

modelling, human model reconstruction, monocular video

Abstract

This paper presents a novel method for reconstructing 3D surface model of human figure from 2D uncalibrated monocular video. Unlike other works on body reconstruction from monocular video where either the source images are strictly selected or the skeleton proportions are assumed available beforehand, the proposed system automatically recovers the skeleton proportions and builds the 3D human body shape without pose estimation. The reconstructed human model is in NURBS format which can be easily used in animation, virtual environment or any other applications.

Important Links:



Go Back