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

Source: [Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences](<https://www.sota2.com/research/paper/68fa64481e209131cea03b3c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:00:11.434Z

Authors: Anil Bas, William A. P. Smith, Timo Bolkart, Stefanie Wuhrer

Published: 2016-02-02T21:43:15.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Face Shape Reconstruction on MICC Florence Faces multi-frame](<https://www.sota2.com/research/sota/3d-face-shape-reconstruction-on-micc-florence-faces-multi-frame.md>): 3D Face Shape Reconstruction; MICC Florence Faces multi-frame; 3DRMSE: 1.84.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1602.01125>)

[PDF](<https://arxiv.org/pdf/1602.01125.pdf>)