PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction

TL;DR

PartNerFace introduces a part-based neural radiance fields approach that improves facial avatar reconstruction from monocular videos by modeling fine-scale motions and unseen expressions.

Contribution

It proposes a novel part-based deformation field with local MLPs and inverse skinning for better generalization and detailed facial motion capture.

Findings

Outperforms state-of-the-art methods quantitatively.

Generalizes well to unseen facial expressions.

Captures fine-scale facial motions effectively.

Abstract

We present PartNerFace, a part-based neural radiance fields approach, for reconstructing animatable facial avatar from monocular RGB videos. Existing solutions either simply condition the implicit network with the morphable model parameters or learn an imaginary canonical radiance field, making them fail to generalize to unseen facial expressions and capture fine-scale motion details. To address these challenges, we first apply inverse skinning based on a parametric head model to map an observed point to the canonical space, and then model fine-scale motions with a part-based deformation field. Our key insight is that the deformation of different facial parts should be modeled differently. Specifically, our part-based deformation field consists of multiple local MLPs to adaptively partition the canonical space into different parts, where the deformation of a 3D point is computed by aggregating the prediction of all local MLPs by a soft-weighting mechanism. Extensive experiments demonstrate that our method generalizes well to unseen expressions and is capable of modeling fine-scale facial motions, outperforming state-of-the-art methods both quantitatively and qualitatively.