GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces

TL;DR

GaussianBlender is a fast, scalable framework for text-driven 3D stylization that produces high-fidelity, multi-view consistent results without per-asset optimization, enabling practical large-scale 3D asset creation.

Contribution

It introduces a novel feed-forward approach with disentangled latent spaces and a diffusion model for instant, high-quality 3D stylization from text prompts.

Findings

Achieves instant stylization with high fidelity.

Maintains multi-view consistency and geometry preservation.

Outperforms optimization-based methods in speed and quality.

Abstract

3D stylization is central to game development, virtual reality, and digital arts, where the demand for diverse assets calls 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.