ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-On
This addresses artifact issues in virtual try-on for applications like e-commerce and fashion, representing an incremental improvement over existing latent diffusion methods.
The paper tackles the problem of boundary artifacts in virtual try-on (VITON) by proposing ART-VITON, a measurement-guided latent diffusion framework that ensures artifact-free synthesis, resulting in improved visual fidelity and robustness over state-of-the-art methods on datasets like VITON-HD, DressCode, and SHHQ-1.0.
Virtual try-on (VITON) aims to generate realistic images of a person wearing a target garment, requiring precise garment alignment in try-on regions and faithful preservation of identity and background in non-try-on regions. While latent diffusion models (LDMs) have advanced alignment and detail synthesis, preserving non-try-on regions remains challenging. A common post-hoc strategy directly replaces these regions with original content, but abrupt transitions often produce boundary artifacts. To overcome this, we reformulate VITON as a linear inverse problem and adopt trajectory-aligned solvers that progressively enforce measurement consistency, reducing abrupt changes in non-try-on regions. However, existing solvers still suffer from semantic drift during generation, leading to artifacts. We propose ART-VITON, a measurement-guided diffusion framework that ensures measurement adherence while maintaining artifact-free synthesis. Our method integrates residual prior-based initialization to mitigate training-inference mismatch and artifact-free measurement-guided sampling that combines data consistency, frequency-level correction, and periodic standard denoising. Experiments on VITON-HD, DressCode, and SHHQ-1.0 demonstrate that ART-VITON effectively preserves identity and background, eliminates boundary artifacts, and consistently improves visual fidelity and robustness over state-of-the-art baselines.