Deep Semantic Manipulation of Facial Videos

TL;DR

This paper introduces a neural rendering method for interactive, semantic facial video manipulation that allows users to control expressions via intuitive labels, producing photorealistic results with promising applications.

Contribution

The work presents a novel disentangled 3D facial expression model linked to semantic emotion labels, enabling user-friendly, controllable facial video editing.

Findings

Effective semantic control of facial expressions in videos.

Photorealistic manipulation with promising qualitative and quantitative results.

User-friendly interactive AI tool for facial video editing.

Abstract

Editing and manipulating facial features in videos is an interesting and important field of research with a plethora of applications, ranging from movie post-production and visual effects to realistic avatars for video games and virtual assistants. Our method supports semantic video manipulation based on neural rendering and 3D-based facial expression modelling. We focus on interactive manipulation of the videos by altering and controlling the facial expressions, achieving promising photorealistic results. The proposed method is based on a disentangled representation and estimation of the 3D facial shape and activity, providing the user with intuitive and easy-to-use control of the facial expressions in the input video. We also introduce a user-friendly, interactive AI tool that processes human-readable semantic labels about the desired expression manipulations in specific parts of the input video and synthesizes photorealistic manipulated videos. We achieve that by mapping the emotion labels to points on the Valence-Arousal space (where Valence quantifies how positive or negative is an emotion and Arousal quantifies the power of the emotion activation), which in turn are mapped to disentangled 3D facial expressions through an especially-designed and trained expression decoder network. The paper presents detailed qualitative and quantitative experiments, which demonstrate the effectiveness of our system and the promising results it achieves.