Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model

TL;DR

This paper introduces the first automatic method for landmark detection and 3D face reconstruction of caricatures using a novel nonlinear parametric model and a neural network trained on a new dataset, addressing a challenging problem in artistic face modeling.

Contribution

It presents a new dataset, a nonlinear parametric model, and a neural network approach for automatic 3D caricature face reconstruction, which was not previously studied.

Findings

The method effectively reconstructs 3D faces from diverse caricatures.

A new dataset of caricatures and 3D shapes was created.

The approach outperforms existing methods in accuracy and robustness.

Abstract

Caricature is an artistic abstraction of the human face by distorting or exaggerating certain facial features, while still retains a likeness with the given face. Due to the large diversity of geometric and texture variations, automatic landmark detection and 3D face reconstruction for caricature is a challenging problem and has rarely been studied before. In this paper, we propose the first automatic method for this task by a novel 3D approach. To this end, we first build a dataset with various styles of 2D caricatures and their corresponding 3D shapes, and then build a parametric model on vertex based deformation space for 3D caricature face. Based on the constructed dataset and the nonlinear parametric model, we propose a neural network based method to regress the 3D face shape and orientation from the input 2D caricature image. Ablation studies and comparison with state-of-the-art methods demonstrate the effectiveness of our algorithm design. Extensive experimental results demonstrate that our method works well for various caricatures. Our constructed dataset, source code and trained model are available at https://github.com/Juyong/CaricatureFace.