OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance

TL;DR

OmniVTON++ introduces a training-free, diffusion-based virtual try-on framework that generalizes across in-shop and in-the-wild settings. It decomposes the problem into Structured Garment Morphing for geometry-aware garment adaptation, Principal Pose Guidance for step-wise pose control during diffusion sampling, and Continuous Boundary Stitching for boundary coherence, augmented by Positional Index Realignment for diffusion-transformer backbones. Across cross-dataset, cross-garment-type, multi-garment, multi-human, and anime-character experiments, it achieves state-of-the-art generalization without retraining and demonstrates robustness to backbone variations. The approach broadens VTON applicability, enabling a single, training-free pipeline to handle diverse garments and characters with practical deployment potential.

Abstract

Image-based Virtual Try-On (VTON) concerns the synthesis of realistic person imagery through garment re-rendering under human pose and body constraints. In practice, however, existing approaches are typically optimized for specific data conditions, making their deployment reliant on retraining and limiting their generalization as a unified solution. We present OmniVTON++, a training-free VTON framework designed for universal applicability. It addresses the intertwined challenges of garment alignment, human structural coherence, and boundary continuity by coordinating Structured Garment Morphing for correspondence-driven garment adaptation, Principal Pose Guidance for step-wise structural regulation during diffusion sampling, and Continuous Boundary Stitching for boundary-aware refinement, forming a cohesive pipeline without task-specific retraining. Experimental results demonstrate that OmniVTON++ achieves state-of-the-art performance across diverse generalization settings, including cross-dataset and cross-garment-type evaluations, while reliably operating across scenarios and diffusion backbones within a single formulation. In addition to single-garment, single-human cases, the framework supports multi-garment, multi-human, and anime character virtual try-on, expanding the scope of virtual try-on applications. The source code will be released to the public.

Figures (13)

• Figure 1: We present OmniVTON++, a training-free framework that unifies virtual try-on from in-shop to in-the-wild. It accommodates varied garment sources and person inputs, maintaining consistent garment geometry, texture, and human structure. Notably, OmniVTON++ unlocks multi-garment, multi-human, and anime virtual try-on beyond traditional real-person single-instance settings, all without additional tuning.
• Figure 2: Overview of OmniVTON++. OmniVTON++ performs Structured Garment Morphing (SGM) to obtain an adapted garment prior, which is incorporated into garment-infused image inpainting, where Principal Pose Guidance (PPG) enforces pose alignment and Continuous Boundary Stitching (CBS) improves boundary consistency across different model backbones. The crossed-circle marker ($\oslash$) indicates components derived from OmniVTON that are not included in the extended journal version.
• Figure 3: Pose guidance mechanisms in OmniVTON and OmniVTON++. (a) Spectral Pose Injection (SPI) in OmniVTON incorporates human structure only at initialization by combining random noise with an inverted latent. (b) Principal Pose Guidance (PPG) in OmniVTON++ enforces pose-consistent structure throughout diffusion sampling via step-wise noise selection, guided by a proxy latent. (c) A proxy image is constructed via ordered region-wise composition to preserve pose while excluding garment appearance.
• Figure 4: Cross-stream correspondence in CBS and CBS-DiT on DiT backbones. Person-stream attention is shown as an illustrative example. (a) CBS exhibits positional ambiguity under a shared positional space. (b) CBS-DiT with Positional Index Realignment (PIR) establishes a continuous positional space, yielding aligned correspondence.
• Figure 5: Qualitative results under cross-dataset and cross-garment-type evaluation. Upper-garment try-on results on VITON-HD are shown on the top, while lower-garment and dress results on DressCode are shown on the bottom.