F3G-Avatar : Face Focused Full-body Gaussian Avatar

TL;DR

F3G-Avatar is a novel face-aware full-body avatar synthesis method that enhances facial detail preservation and realism using a two-branch architecture and face-specific training objectives.

Contribution

It introduces a face-focused deformation branch and a new training scheme to improve facial geometry and expression details in full-body avatars.

Findings

Achieves high-quality rendering with PSNR of 26.243 on AvatarReX.

Face-view performance significantly improved with the proposed method.

Ablation studies confirm the effectiveness of the face-focused deformation branch.

Abstract

Existing full-body Gaussian avatar methods primarily optimize global reconstruction quality and often fail to preserve fine-grained facial geometry and expression details. This challenge arises from limited facial representational capacity that causes difficulties in modeling high-frequency pose-dependent deformations. To address this, we propose F3G-Avatar, a full-body, face-aware avatar synthesis method that reconstructs animatable human representations from multi-view RGB video and regressed pose/shape parameters. Starting from a clothed Momentum Human Rig (MHR) template, front/back positional maps are rendered and decoded into 3D Gaussians through a two-branch architecture: a body branch that captures pose-dependent non-rigid deformations and a face-focused deformation branch that refines head geometry and appearance. The predicted Gaussians are fused, posed with linear blend skinning (LBS), and rendered with differentiable Gaussian splatting. Training combines reconstruction and perceptual objectives with a face-specific adversarial loss to enhance realism in close-up views. Experiments demonstrate strong rendering quality, with face-view performance reaching PSNR/SSIM/LPIPS of 26.243/0.964/0.084 on the AvatarReX dataset. Ablations further highlight contributions of the MHR template and the face-focused deformation. F3G-Avatar provides a practical, high-quality pipeline for realistic, animatable full-body avatar synthesis.