Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences

TL;DR

This paper introduces an automatic method for fitting 3D face models to images using geometric features, showing that hard correspondences outperform soft ones in accuracy.

Contribution

The paper presents a novel automatic fitting approach that employs hard correspondences between model vertices and image edges, improving over soft correspondence methods.

Findings

Hard correspondence method yields more accurate fits.

Automatic fitting works across arbitrary pose and lighting.

Hard vs. soft correspondence comparison demonstrates superiority.

Abstract

We propose a fully automatic method for fitting a 3D morphable model to single face images in arbitrary pose and lighting. Our approach relies on geometric features (edges and landmarks) and, inspired by the iterated closest point algorithm, is based on computing hard correspondences between model vertices and edge pixels. We demonstrate that this is superior to previous work that uses soft correspondences to form an edge-derived cost surface that is minimised by nonlinear optimisation.