Geometry Driven Progressive Warping for One-Shot Face Animation

TL;DR

This paper introduces a geometry-driven progressive warping method for one-shot face animation, utilizing geometric patterns and a progressive warping module to improve displacement estimation and synthesis quality.

Contribution

It proposes a novel geometry-guided model with a progressive warping module that enhances displacement estimation for realistic face animation.

Findings

Achieves state-of-the-art results on VoxCeleb datasets.

Produces high-fidelity portrait videos with improved displacement accuracy.

Effectively models displacements beyond face regions using source features.

Abstract

Face animation aims at creating photo-realistic portrait videos with animated poses and expressions. A common practice is to generate displacement fields that are used to warp pixels and features from source to target. However, prior attempts often produce sub-optimal displacements. In this work, we present a geometry driven model and propose two geometric patterns as guidance: 3D face rendered displacement maps and posed neural codes. The model can optionally use one of the patterns as guidance for displacement estimation. To model displacements at locations not covered by the face model (e.g., hair), we resort to source image features for contextual information and propose a progressive warping module that alternates between feature warping and displacement estimation at increasing resolutions. We show that the proposed model can synthesize portrait videos with high fidelity and achieve the new state-of-the-art results on the VoxCeleb1 and VoxCeleb2 datasets for both cross identity and same identity reconstruction.