IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter

TL;DR

IPVTON introduces a novel 3D virtual try-on framework that uses image prompts and diffusion models to accurately generate 3D human models wearing target garments, improving realism and geometric consistency.

Contribution

The paper presents IPVTON, a new image-based 3D virtual try-on method that integrates image prompt adapters and mask-guided embeddings for enhanced accuracy and realism.

Findings

Outperforms previous methods in geometry and texture quality

Effectively retains source identity shape while fitting target garments

Demonstrates superior results in qualitative and quantitative evaluations

Abstract

Given a pair of images depicting a person and a garment separately, image-based 3D virtual try-on methods aim to reconstruct a 3D human model that realistically portrays the person wearing the desired garment. In this paper, we present IPVTON, a novel image-based 3D virtual try-on framework. IPVTON employs score distillation sampling with image prompts to optimize a hybrid 3D human representation, integrating target garment features into diffusion priors through an image prompt adapter. To avoid interference with non-target areas, we leverage mask-guided image prompt embeddings to focus the image features on the try-on regions. Moreover, we impose geometric constraints on the 3D model with a pseudo silhouette generated by ControlNet, ensuring that the clothed 3D human model retains the shape of the source identity while accurately wearing the target garments. Extensive qualitative and quantitative experiments demonstrate that IPVTON outperforms previous methods in image-based 3D virtual try-on tasks, excelling in both geometry and texture.