Structure-Detail Decoupled Autoregressive Generation for Fast and High-Fidelity Virtual Try-On

• URL: http://arxiv.org/abs/2607.11233v1
• Date: Mon, 13 Jul 2026 08:21:43 GMT
• Title: Structure-Detail Decoupled Autoregressive Generation for Fast and High-Fidelity Virtual Try-On
• Abstract summary: Virtual try-on (VTON) is a bi-conditional image generation problem.<n> Diffusion-based VTON methods suffer from high-frequency detail loss due to inherent latent compression.<n>Recent visual autoregressive models offer a promising alternative for high-quality generation.
• Score: 51.92060872944388
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Virtual try-on (VTON) is a bi-conditional image generation problem that requires not only accurate person preservation but also faithful garment deformation and detail synthesis. Diffusion-based VTON methods can jointly model these factors in a compressed latent space, but suffer from high-frequency detail loss due to inherent latent compression, even with costly multi-step denoising. Recent visual autoregressive (VAR) models offer a promising alternative for high-quality generation with faster inference, yet remain unexplored for VTON due to the lack of effective bi-conditioning mechanisms. To bridge this gap, we first introduce VAR-VTON, a VAR-based VTON model that incorporates garment conditioning and structural guidance for efficient latent-space VTON. Despite its efficacy, latent-space generation still struggles to preserve fine-grained garment details. We argue that different VTON sub-tasks should be addressed in different representation spaces: structural synthesis such as garment warping and person layout is suited to the latent space, whereas fine-grained detail recovery should be tackled in the pixel space. Motivated by this insight, we further propose STAR-VTON, a Two-Stage AutoRegressive framework that builds upon VAR-VTON by decoupling latent-space structural synthesis from pixel-space detail recovery. Our idea is to resort to a matching-informed refiner to establish dense correspondences between the stage-one generation and the source garment to directly map fine-grained pixel-space details. Extensive experiments show that STAR-VTON achieves an impressive efficiency-fidelity trade-off: VAR-VTON runs at least $4\times$ faster than diffusion-based counterparts without degrading quality, and the pixel-space refiner effectively restores fine details and acts as a plug-and-play module that can benefit existing VTON approaches.

Related papers

• LPH-VTON: Resolving the Structure-Texture Dilemma of Virtual Try-On via Latent Process Handover [15.242291833451882]
  Virtual Try-On aims to synthesize photorealistic images of garments precisely aligned with a person's body and pose.<n>Current diffusion-based methods, however, face a fundamental trade-off between structural integrity and textural fidelity.<n>We propose LPH-VTON, a new synergistic framework that resolves this tension within a single, continuous denoising process.
  arXiv  Detail & Related papers  (2026-05-14T14:18:56Z)
• OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework [16.89102936125974]
  We propose OmniDiT, an omni Virtual Try-On framework based on the Diffusion Transformer.<n>We first establish a self-evolving data curation pipeline to continuously produce data, and construct a large VTON dataset Omni-TryOn.<n>We are the first to introduce Shifted Window Attention into the diffusion model, thus achieving a linear complexity.
  arXiv  Detail & Related papers  (2026-03-20T05:04:55Z)
• V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising [65.5867130156805]
  We present V-Co, a systematic study of visual co-denoising in a unified JiT-based framework.<n>Our study reveals four key ingredients for effective visual co-denoising.<n>V-Co outperforms the underlying pixel-space diffusion baseline and strong prior pixel-diffusion methods.
  arXiv  Detail & Related papers  (2026-03-17T17:01:54Z)
• PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On [39.47263059671598]
  VTON is a structured image editing problem that demands strong conditional generation under three key requirements.<n>We present PROMO, a promptable virtual try-on framework built upon a Flow Matching DiT backbone with latent multi-modal conditional concatenation.<n>On standard benchmarks, PROMO surpasses both prior VTON methods and general image editing models in visual fidelity while delivering a competitive balance between quality and speed.
  arXiv  Detail & Related papers  (2026-03-12T08:41:05Z)
• Mobile-VTON: High-Fidelity On-Device Virtual Try-On [75.5009105664896]
  Mobile-VTON is a high-quality, privacy-preserving framework for virtual try-on.<n>It enables fully offline virtual try-on on commodity mobile devices using only a single user image and a garment image.
  arXiv  Detail & Related papers  (2026-03-01T06:36:13Z)
• One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion [57.824020826432815]
  We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images.<n>We design a Dual-Domain Detail Perception Module, which enables handling high-resolution images without being limited by the ViT backbone.<n>We develop a feature-guided diffusion network, which can preserve high-frequency details during the restoration process.
  arXiv  Detail & Related papers  (2026-01-20T17:11:55Z)
• Rethinking Garment Conditioning in Diffusion-based Virtual Try-On [7.386027762996787]
  We develop Re-CatVTON, an efficient single UNet model that achieves high performance.<n>The proposed Re-CatVTON significantly improves performance compared to its predecessor.<n>Our results demonstrate improved FID, KID, and LPIPS scores, with only a marginal decrease in SSIM.
  arXiv  Detail & Related papers  (2025-11-24T05:19:44Z)
• Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement [89.99237142387655]
  We introduce LH-VAE, which enhances semantic robustness through visual semantic constraints and progressive degradations.<n>Latent Harmony is a two-stage framework that redefines VAEs for UHD restoration by jointly regularizing the latent space and enforcing high-frequency-aware reconstruction.<n>Experiments show Latent Harmony achieves state-of-the-art performance across UHD and standard-resolution tasks, effectively balancing efficiency, perceptual quality, and reconstruction accuracy.
  arXiv  Detail & Related papers  (2025-10-09T08:54:26Z)
• OmniVTON: Training-Free Universal Virtual Try-On [53.31945401098557]
  Image-based Virtual Try-On (VTON) techniques rely on either supervised in-shop approaches, or unsupervised in-the-wild methods, which improve adaptability but remain constrained by data biases and limited universality.<n>We propose OmniVTON, the first training-free universal VTON framework that decouples garment and pose conditioning to achieve both texture fidelity and pose consistency across diverse settings.
  arXiv  Detail & Related papers  (2025-07-20T16:37:53Z)
• DS-VTON: An Enhanced Dual-Scale Coarse-to-Fine Framework for Virtual Try-On [33.05238077456732]
  We propose DS-VTON, an enhanced dual-scale coarse-to-fine framework for virtual try-on.<n> DS-VTON consists of two stages: the first generates a low-resolution try-on result to capture the semantic correspondence between garment and body.<n>In the second stage, a blend-refine diffusion process reconstructs high-resolution outputs by refining the residual between scales.
  arXiv  Detail & Related papers  (2025-06-01T08:52:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.