Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars

arXiv:2607.28032v1 Announce Type: new Abstract: Creating photorealistic animatable head avatars from a single image remains a fundamental challenge in digital human synthesis. While recent 3D Gaussian Splatting methods have achieved promising results, they rely on external tracking pipelines whose latency is excluded from inference measurements. Furthermore, they adopt unified representations that entangle geometrically distinct facial regions, limiting both expressiveness and rendering fidelity. We propose SpiD (Split and Drive), a single-image Gaussian head avatar framework built on two disentanglement axes. The compute axis internalizes per-frame driving, eliminating external tracking dependency at inference. The feature axis decomposes the avatar into three specialized Gaussian branches, each modeling a geometrically distinct facial domain. Extensive experiments demonstrate consistently strong performance against state-of-the-art methods while achieving the fastest inference speed among all compared methods on a single GPU with the complete driving pipeline included.

Related

• SIE3D: Single-Image Expressive 3D Avatar Generation via Semantic Embedding and Perceptual Expression Loss
• RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction
• Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
• PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

Source: arXiv cs.CV | 2026-07-31