MoGaFace: Momentum-Guided and Texture-Aware Gaussian Avatars for Consistent Facial Geometry
This work addresses the challenge of consistent and detailed 3D head avatar modeling for applications in computer vision and graphics, representing an incremental improvement over existing two-stage methods.
The paper tackled the problem of misalignment between estimated FLAME meshes and target images in 3D head avatar reconstruction, which leads to suboptimal rendering quality and loss of fine details, by introducing MoGaFace, a framework that continuously refines facial geometry and texture attributes during Gaussian rendering, achieving high-fidelity reconstruction and significantly improved novel-view synthesis quality.
Existing 3D head avatar reconstruction methods adopt a two-stage process, relying on tracked FLAME meshes derived from facial landmarks, followed by Gaussian-based rendering. However, misalignment between the estimated mesh and target images often leads to suboptimal rendering quality and loss of fine visual details. In this paper, we present MoGaFace, a novel 3D head avatar modeling framework that continuously refines facial geometry and texture attributes throughout the Gaussian rendering process. To address the misalignment between estimated FLAME meshes and target images, we introduce the Momentum-Guided Consistent Geometry module, which incorporates a momentum-updated expression bank and an expression-aware correction mechanism to ensure temporal and multi-view consistency. Additionally, we propose Latent Texture Attention, which encodes compact multi-view features into head-aware representations, enabling geometry-aware texture refinement via integration into Gaussians. Extensive experiments show that MoGaFace achieves high-fidelity head avatar reconstruction and significantly improves novel-view synthesis quality, even under inaccurate mesh initialization and unconstrained real-world settings.