DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport

TL;DR

DirectTryOn introduces a one-step virtual try-on method that leverages the constrained structure of the task to achieve high-quality results efficiently, reducing inference cost significantly.

Contribution

The paper proposes a novel one-step VTON approach using straightened conditional transport and introduces specific losses and distillation to align pretrained models with task constraints.

Findings

Achieves state-of-the-art results with one-step sampling.

Reduces inference cost compared to multi-step diffusion and flow-based methods.

Demonstrates high-quality virtual try-on performance.

Abstract

Recent diffusion- and flow-based VTON methods achieve strong results with pretrained generative models, but their reliance on multi-step sampling incurs high inference cost, while existing acceleration methods largely overlook the intrinsic structure of the try-on task. In this paper, we highlight a key observation: VTON outputs are highly constrained by the conditional inputs, suggesting that the conditional sampling trajectory can be much straighter than that in general image generation, making one-step generation a natural solution. However, limited task-specific data makes training from scratch impractical, forcing existing methods to fine-tune pretrained models whose objectives do not encourage such straight conditional trajectories. Thus, the deviation from an ideal straight path mainly comes from the mismatch between pretrained base models and the conditional nature of try-on generation, rather than from the task itself. Motivated by this insight, we encourage straighter VTON sampling trajectories through three targeted modifications: pure conditional transport, a garment preservation loss, and a self consistency loss. We further introduce a one-step distillation stage. Extensive experiments show that our method achieves state-of-the-art performance with one-step sampling, establishing a new standard for efficient and high-quality VTON.