Alive Caricature from 2D to 3D

TL;DR

This paper introduces a novel algorithm to generate expressive 3D caricatures from 2D images using an intrinsic deformation representation, enabling exaggerated face models with minimal user input.

Contribution

It presents a new deformation space and an optimization model that automatically creates 3D caricatures from 2D images, surpassing classical parametric models in expressiveness.

Findings

Outperforms classical parametric face models in expressiveness.

Uses standard face datasets without complex 3D caricature training sets.

Provides flexible and automatic 3D caricature generation from 2D images.

Abstract

Caricature is an art form that expresses subjects in abstract, simple and exaggerated view. While many caricatures are 2D images, this paper presents an algorithm for creating expressive 3D caricatures from 2D caricature images with a minimum of user interaction. The key idea of our approach is to introduce an intrinsic deformation representation that has a capacity of extrapolation enabling us to create a deformation space from standard face dataset, which maintains face constraints and meanwhile is sufficiently large for producing exaggerated face models. Built upon the proposed deformation representation, an optimization model is formulated to find the 3D caricature that captures the style of the 2D caricature image automatically. The experiments show that our approach has better capability in expressing caricatures than those fitting approaches directly using classical parametric face models such as 3DMM and FaceWareHouse. Moreover, our approach is based on standard face datasets and avoids constructing complicated 3D caricature training set, which provides great flexibility in real applications.