GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction

TL;DR

This paper introduces a 3D Gaussian-based head model that accurately captures complex head details, enabling high-quality, real-time, monocular head avatar reconstruction from limited data, surpassing previous methods in quality and speed.

Contribution

The novel 3D Gaussian Parametric Head Model effectively models intricate head details and expressions, providing a robust, efficient framework for high-quality avatar reconstruction from minimal input data.

Findings

Achieves photo-realistic rendering with real-time efficiency.

Enables high-quality head avatar reconstruction from monocular video or few-shot data.

Surpasses previous methods in reconstruction quality and training speed.

Abstract

Creating high-fidelity 3D human head avatars is crucial for applications in VR/AR, digital human, and film production. Recent advances have leveraged morphable face models to generate animated head avatars from easily accessible data, representing varying identities and expressions within a low-dimensional parametric space. However, existing methods often struggle with modeling complex appearance details, e.g., hairstyles, and suffer from low rendering quality and efficiency. In this paper we introduce a novel approach, 3D Gaussian Parametric Head Model, which employs 3D Gaussians to accurately represent the complexities of the human head, allowing precise control over both identity and expression. The Gaussian model can handle intricate details, enabling realistic representations of varying appearances and complex expressions. Furthermore, we presents a well-designed training framework to ensure smooth convergence, providing a robust guarantee for learning the rich content. Our method achieves high-quality, photo-realistic rendering with real-time efficiency, making it a valuable contribution to the field of parametric head models. Finally, we apply the 3D Gaussian Parametric Head Model to monocular video or few-shot head avatar reconstruction tasks, which enables instant reconstruction of high-quality 3D head avatars even when input data is extremely limited, surpassing previous methods in terms of reconstruction quality and training speed.