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

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.

To appear in ACCV 2016 Workshop on Facial Informatics

References in corpus (2)

• Review of Statistical Shape Spaces for 3D Data with Comparative Analysis for Human Faces
• Fitting 3D Morphable Models using Local Features

Cited by in corpus (11)

• 3D Face Reconstruction with Geometry Details from a Single Image
• Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
• Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction
• Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
• Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
• On 3D Face Reconstruction via Cascaded Regression in Shape Space
• Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
• CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images
• SPARK: Self-supervised Personalized Real-time Monocular Face Capture
• High Accuracy Face Geometry Capture using a Smartphone Video
• Topologically Consistent Multi-View Face Inference Using Volumetric Sampling