# Cartoonish sketch-based face editing in videos using identity deformation transfer

## TL;DR

This paper introduces a novel method for editing faces in videos using hand-drawn sketches, by reconstructing 3D face models and transferring deformations to achieve consistent, high-fidelity facial modifications.

## Contribution

It presents a new identity deformation algorithm that transfers 2D sketch-based facial edits to 3D models for video face editing.

## Key findings

- Effective facial editing in videos using sketches demonstrated.
- High consistency and fidelity in facial modifications achieved.
- User study confirms usability and effectiveness.

## Abstract

We address the problem of using hand-drawn sketches to create exaggerated deformations to faces in videos, such as enlarging the shape or modifying the position of eyes or mouth. This task is formulated as a 3D face model reconstruction and deformation problem. We first recover the facial identity and expressions from the video by fitting a face morphable model for each frame. At the same time, user's editing intention is recognized from input sketches as a set of facial modifications. Then a novel identity deformation algorithm is proposed to transfer these facial deformations from 2D space to the 3D facial identity directly while preserving the facial expressions. After an optional stage for further refining the 3D face model, these changes are propagated to the whole video with the modified identity. Both the user study and experimental results demonstrate that our sketching framework can help users effectively edit facial identities in videos, while high consistency and fidelity are ensured at the same time.