GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting

TL;DR

GaussianVTON introduces a novel 3D virtual try-on pipeline that leverages Gaussian Splatting and image prompts, enabling high-quality, multi-stage editing of 3D human models with minimal data and addressing common editing issues.

Contribution

It pioneers the use of only images as prompts for 3D editing and proposes a three-stage refinement and ERR strategy to improve editing quality and geometric consistency.

Findings

Outperforms previous 3D VTON methods in quality and flexibility.

Effectively mitigates face blurring and garment inaccuracies.

Establishes a new paradigm for image-prompted 3D scene editing.

Abstract

The increasing prominence of e-commerce has underscored the importance of Virtual Try-On (VTON). However, previous studies predominantly focus on the 2D realm and rely heavily on extensive data for training. Research on 3D VTON primarily centers on garment-body shape compatibility, a topic extensively covered in 2D VTON. Thanks to advances in 3D scene editing, a 2D diffusion model has now been adapted for 3D editing via multi-viewpoint editing. In this work, we propose GaussianVTON, an innovative 3D VTON pipeline integrating Gaussian Splatting (GS) editing with 2D VTON. To facilitate a seamless transition from 2D to 3D VTON, we propose, for the first time, the use of only images as editing prompts for 3D editing. To further address issues, e.g., face blurring, garment inaccuracy, and degraded viewpoint quality during editing, we devise a three-stage refinement strategy to gradually mitigate potential issues. Furthermore, we introduce a new editing strategy termed Edit Recall Reconstruction (ERR) to tackle the limitations of previous editing strategies in leading to complex geometric changes. Our comprehensive experiments demonstrate the superiority of GaussianVTON, offering a novel perspective on 3D VTON while also establishing a novel starting point for image-prompting 3D scene editing.