Fitting 3D Morphable Models using Local Features

TL;DR

This paper introduces a fast, learning-based method for fitting 3D Morphable Models to 2D images using local features, improving robustness and enabling real-time applications.

Contribution

It presents the first use of local features for Morphable Model fitting, employing a cascaded regression approach that learns gradients to optimize shape and pose parameters.

Findings

Robustness against imaging variations demonstrated

Method achieves real-time performance

Effective on both synthetic and real data

Abstract

In this paper, we propose a novel fitting method that uses local image features to fit a 3D Morphable Model to 2D images. To overcome the obstacle of optimising a cost function that contains a non-differentiable feature extraction operator, we use a learning-based cascaded regression method that learns the gradient direction from data. The method allows to simultaneously solve for shape and pose parameters. Our method is thoroughly evaluated on Morphable Model generated data and first results on real data are presented. Compared to traditional fitting methods, which use simple raw features like pixel colour or edge maps, local features have been shown to be much more robust against variations in imaging conditions. Our approach is unique in that we are the first to use local features to fit a Morphable Model. Because of the speed of our method, it is applicable for realtime applications. Our cascaded regression framework is available as an open source library (https://github.com/patrikhuber).