Edit3DGS: Unified Framework for Dynamic Head Editing via 2D Instruction-Guided Diffusion and 3D Gaussian Splatting
This work addresses the challenge of temporally consistent, controllable 3D head editing from video for applications in virtual avatars and media production, offering a unified solution that outperforms separate frame-based or static approaches.
Edit3DGS introduces a unified framework for dynamic 3D head editing that combines 2D instruction-guided diffusion with 3D Gaussian splatting, enabling fine-grained edits like expression transformation and attribute modification while maintaining temporal consistency and identity preservation. The method achieves artifact-free, high-fidelity avatar editing with smooth temporal transitions.
We present Edit3DGS, a unified framework for dynamic 3D head editing that integrates 2D instruction-guided diffusion with 3D Gaussian splatting. Unlike prior approaches that separately address frame-based edits or static 3D reconstruction, our method couples semantic controllability in the image domain with photorealistic, temporally consistent 3D representations. Given an input video, editable facial regions are masked and modified using a text-conditioned diffusion model to support fine-grained operations such as expression transformation, attribute modification, and appearance refinement. The edited frames are then aggregated through 3D Gaussian splatting to produce a coherent, high-fidelity avatar that preserves both identity and motion dynamics. To enforce consistency, Edit3DGS incorporates multi-view batch editing and lightweight inpainting strategies that recover lost expressions across timesteps. Experimental results demonstrate that our framework enables controllable, artifact-free head editing with smooth temporal transitions, offering practical applications in virtual avatars, immersive communication, film production, and interactive media.