Paper Info
Title
3D reconstruction of human faces from occluding contours
Abstract
In this paper we take a fresh look at the problem of extracting shape from contours of human faces. We focus on two key questions: how can we robustly fit a 3D face model to a given input contour; and, how much information about shape does a single contour image convey. Our system matches silhouettes and inner contours of a PCA based Morphable Model to an input contour image. We discuss different types of contours in terms of their effect on the continuity and differentiability of related error functions and justify our choices of error function (modified Euclidean Distance Transform) and optimization algorithm (Downhill Simplex). In a synthetic test setting we explore the limits of accuracy when recovering shape and pose from a single correct input contour and find that pose is much better captured by contours than is shape. In a semi-synthetic test setting - the input images are edges extracted from photorealistic renderings of the PCA model - we investigate the robustness of our method and argue that not all discrepancies between edges and contours can be solved by the fitting process alone.
Year
DOI
Venue
2007
10.1007/978-3-540-71457-6_24
MIRAGE
Keywords
Field
DocType
related error function,inner contour,human face,single correct input contour,pca model,input contour,input image,input contour image,face model,occluding contour,single contour image,error function,euclidean distance,3d reconstruction
Computer vision,Error function,Pattern recognition,Computer science,Simplex,Robustness (computer science),Differentiable function,Ground truth,Optimization algorithm,Artificial intelligence,Rendering (computer graphics),3D reconstruction
Conference
Volume
ISSN
Citations 
4418
0302-9743
4
PageRank 
References 
Authors
0.45
11
3
Name
Order
Citations
PageRank
Michael Keller140.45
Reinhard Knothe22749.66
Thomas Vetter34528529.79