Interactive 3D Face Stylization Using Sculptural Abstraction



Jan Jachnik (Imperial College London),
Dan B Goldman (Adobe Research),
Linjie Luo (Adobe Research),
Andrew J. Davison (Imperial College London).

This work was started as part of Jan’s internship at Adobe Research and then continued as a collaboration with Imperial College London.


Sculptors often deviate from geometric accuracy in order to enhance the appearance of their sculpture. These subtle stylizations may emphasize anatomy, draw the viewer’s focus to characteristic features of the subject, or symbolize textures that might not be accurately reproduced in a particular sculptural medium, while still retaining fidelity to the unique proportions of an individual. In this work we demonstrate an interactive system for enhancing face geometry using a class of stylizations based on visual decomposition into abstract semantic regions, which we call sculptural abstraction. We propose an interactive two-scale optimization framework for stylization based on sculptural abstraction, allowing real-time adjustment of both global and local parameters. We demonstrate this system’s effectiveness in enhancing physical 3D prints of scans from various sources.



The paper can be downloaded here:

A selection of the results, including the segmentation, abstracted mesh and stylized results are made available for download.

Some of the files in the download are copyrighted and licensed under the Creative Commons – Attribution – Non-Commercial license. By downloading these files you agree to abide by the license.

[Download – 80MB]

Delicious Twitter Digg this StumbleUpon Facebook