OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework

📰 ArXiv cs.AI

OmniDiT extends Diffusion Transformer to an omni Virtual Try-On framework for improved detail preservation and generalization

advanced Published 23 Mar 2026

Action Steps

Combine try-on and try-off tasks into a unified model using Diffusion Transformer
Address fine-grained detail preservation and generalization to complex scenes
Simplify the pipeline and improve efficient inference

Who Needs to Know This

Computer vision engineers and researchers on a team can benefit from OmniDiT as it tackles challenges in Virtual Try-On technologies, while product managers can leverage it to improve customer experience

Key Insight

💡 OmniDiT combines try-on and try-off tasks for improved performance

Key Takeaways

OmniDiT extends Diffusion Transformer to an omni Virtual Try-On framework for improved detail preservation and generalization

Full Article

Title: OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework

Abstract:
arXiv:2603.19643v1 Announce Type: cross Abstract: Despite the rapid advancement of Virtual Try-On (VTON) and Try-Off (VTOFF) technologies, existing VTON methods face challenges with fine-grained detail preservation, generalization to complex scenes, complicated pipeline, and efficient inference. To tackle these problems, we propose OmniDiT, an omni Virtual Try-On framework based on the Diffusion Transformer, which combines try-on and try-off tasks into one unified model. Specifically, we first e

Read full paper → ← Back to Reads