High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

TL;DR

This paper introduces a novel spatially-varying expression conditioning method for neural radiance fields, significantly improving the realism and detail in 3D head avatar reconstruction, especially in facial expressions.

Contribution

The paper proposes a new SVE conditioning approach and a coarse-to-fine training strategy to enhance facial expression detail and rendering quality in 3D head avatars.

Findings

Outperforms state-of-the-art methods in rendering quality

Achieves higher geometric detail in 3D head avatars

Effective on mobile phone-collected datasets

Abstract

One crucial aspect of 3D head avatar reconstruction lies in the details of facial expressions. Although recent NeRF-based photo-realistic 3D head avatar methods achieve high-quality avatar rendering, they still encounter challenges retaining intricate facial expression details because they overlook the potential of specific expression variations at different spatial positions when conditioning the radiance field. Motivated by this observation, we introduce a novel Spatially-Varying Expression (SVE) conditioning. The SVE can be obtained by a simple MLP-based generation network, encompassing both spatial positional features and global expression information. Benefiting from rich and diverse information of the SVE at different positions, the proposed SVE-conditioned neural radiance field can deal with intricate facial expressions and achieve realistic rendering and geometry details of high-fidelity 3D head avatars. Additionally, to further elevate the geometric and rendering quality, we introduce a new coarse-to-fine training strategy, including a geometry initialization strategy at the coarse stage and an adaptive importance sampling strategy at the fine stage. Extensive experiments indicate that our method outperforms other state-of-the-art (SOTA) methods in rendering and geometry quality on mobile phone-collected and public datasets.