OMEGA-Avatar: One-shot Modeling of 360{\deg} Gaussian Avatars

TL;DR

OMEGA-Avatar is a novel feed-forward framework that creates high-quality, 360-degree, animatable 3D Gaussian head avatars from a single image, addressing hair modeling and multi-view consistency.

Contribution

It introduces two novel modules: a semantic-aware mesh deformation for hair modeling and a multi-view feature splatting for 360-degree consistency, enabling simultaneous full-head, generalizable, and animatable avatar generation.

Findings

Achieves state-of-the-art 360-degree full-head completeness

Outperforms existing methods in identity preservation across views

Maintains global structure and local details without per-instance optimization

Abstract

Creating high-fidelity, animatable 3D avatars from a single image remains a formidable challenge. We identified three desirable attributes of avatar generation: 1) the method should be feed-forward, 2) model a 360{\deg} full-head, and 3) should be animation-ready. However, current work addresses only two of the three points simultaneously. To address these limitations, we propose OMEGA-Avatar, the first feed-forward framework that simultaneously generates a generalizable, 360{\deg}-complete, and animatable 3D Gaussian head from a single image. Starting from a feed-forward and animatable framework, we address the 360{\deg} full-head avatar generation problem with two novel components. First, to overcome poor hair modeling in full-head avatar generation, we introduce a semantic-aware mesh deformation module that integrates multi-view normals to optimize a FLAME head with hair while preserving its topology structure. Second, to enable effective feed-forward decoding of full-head features, we propose a multi-view feature splatting module that constructs a shared canonical UV representation from features across multiple views through differentiable bilinear splatting, hierarchical UV mapping, and visibility-aware fusion. This approach preserves both global structural coherence and local high-frequency details across all viewpoints, ensuring 360{\deg} consistency without per-instance optimization. Extensive experiments demonstrate that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360{\deg} full-head completeness while robustly preserving identity across different viewpoints.