Control4D: Efficient 4D Portrait Editing with Text

TL;DR

Control4D introduces a novel 4D representation and a generator-based approach to enable efficient, consistent, and high-quality text-driven editing of dynamic 4D portraits, overcoming limitations of previous methods.

Contribution

The paper presents GaussianPlanes, a structured 4D representation, and leverages a 4D generator to improve efficiency and consistency in 4D portrait editing from text instructions.

Findings

Reduced training time significantly

Achieved high-quality 4D rendering

Maintained spatial-temporal consistency

Abstract

We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions. Our method addresses the prevalent challenges in 4D editing, notably the inefficiencies of existing 4D representations and the inconsistent editing effect caused by diffusion-based editors. We first propose GaussianPlanes, a novel 4D representation that makes Gaussian Splatting more structured by applying plane-based decomposition in 3D space and time. This enhances both efficiency and robustness in 4D editing. Furthermore, we propose to leverage a 4D generator to learn a more continuous generation space from inconsistent edited images produced by the diffusion-based editor, which effectively improves the consistency and quality of 4D editing. Comprehensive evaluation demonstrates the superiority of Control4D, including significantly reduced training time, high-quality rendering, and spatial-temporal consistency in 4D portrait editing. The link to our project website is https://control4darxiv.github.io.