3D 高斯混合：基于解耦潜在空间的即时风格化
摘要
3D 风格化是游戏开发、虚拟现实和数字艺术的核心任务，众多资产的需求呼tails for scalable methods that support fast, high-fidelity manipulation。Existing text-to-3D stylization methods typically distill from 2D image editors, requiring time-intensive per-asset optimization and exhibiting multi-view inconsistency due to the limitations of current text-to-image models, which makes them impractical for large-scale production. In this paper, we introduce GaussianBlender, a pioneering feed-forward framework for text-driven 3D stylization that performs edits instantly at inference. Our method learns structured, disentangled latent spaces with controlled information sharing for geometry and appearance from spatially-grouped 3D Gaussians. A latent diffusion model then applies text-conditioned edits on these learned representations. Comprehensive evaluations show that GaussianBlender not only delivers instant, high-fidelity, geometry-preserving, multi-view consistent stylization, but also surpasses methods that require per-instance test-time optimization - unlocking practical, democratized 3D stylization at scale。
引用
@article{arxiv.2512.03683,
title = {GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces},
author = {Melis Ocal and Xiaoyan Xing and Yue Li and Ngo Anh Vien and Sezer Karaoglu and Theo Gevers},
journal= {arXiv preprint arXiv:2512.03683},
year = {2025}
}