GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting

TL;DR

GS-VTON introduces a novel 3D virtual try-on method leveraging Gaussian Splatting and diffusion models, enabling consistent, high-quality 3D clothing transfer from 2D models with improved cross-view coherence.

Contribution

The paper presents a new 3D VTON framework using 3D Gaussian Splatting, LoRA fine-tuning, and a reference-driven editing approach, advancing 3D virtual try-on technology.

Findings

Achieves superior fidelity in 3D clothing transfer.

Ensures cross-view consistency and high-quality geometry.

Establishes a new benchmark for 3D VTON evaluation.

Abstract

Diffusion-based 2D virtual try-on (VTON) techniques have recently demonstrated strong performance, while the development of 3D VTON has largely lagged behind. Despite recent advances in text-guided 3D scene editing, integrating 2D VTON into these pipelines to achieve vivid 3D VTON remains challenging. The reasons are twofold. First, text prompts cannot provide sufficient details in describing clothing. Second, 2D VTON results generated from different viewpoints of the same 3D scene lack coherence and spatial relationships, hence frequently leading to appearance inconsistencies and geometric distortions. To resolve these problems, we introduce an image-prompted 3D VTON method (dubbed GS-VTON) which, by leveraging 3D Gaussian Splatting (3DGS) as the 3D representation, enables the transfer of pre-trained knowledge from 2D VTON models to 3D while improving cross-view consistency. (1) Specifically, we propose a personalized diffusion model that utilizes low-rank adaptation (LoRA) fine-tuning to incorporate personalized information into pre-trained 2D VTON models. To achieve effective LoRA training, we introduce a reference-driven image editing approach that enables the simultaneous editing of multi-view images while ensuring consistency. (2) Furthermore, we propose a persona-aware 3DGS editing framework to facilitate effective editing while maintaining consistent cross-view appearance and high-quality 3D geometry. (3) Additionally, we have established a new 3D VTON benchmark, 3D-VTONBench, which facilitates comprehensive qualitative and quantitative 3D VTON evaluations. Through extensive experiments and comparative analyses with existing methods, the proposed \OM has demonstrated superior fidelity and advanced editing capabilities, affirming its effectiveness for 3D VTON.