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

arXiv: https://arxiv.org/abs/2607.11233 · HTML: https://mlsanity.com/paper/2607.11233/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 44 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [VITON: An Image-based Virtual Try-on Network](https://mlsanity.com/paper/1711.08447/) (2017)
- [Toward Characteristic-Preserving Image-based Virtual Try-On Network](https://mlsanity.com/paper/1807.07688/) (2018)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On](https://mlsanity.com/paper/2312.01725/) (2023)
- [Dress Code: High-Resolution Multi-Category Virtual Try-On](https://mlsanity.com/paper/2204.08532/) (2022)
- [LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On](https://mlsanity.com/paper/2305.13501/) (2023)
- [OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on](https://mlsanity.com/paper/2403.01779/) (2024)
- [TryOnDiffusion: A Tale of Two UNets](https://mlsanity.com/paper/2306.08276/) (2023)
- [High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions](https://mlsanity.com/paper/2206.14180/) (2022)
- [Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow](https://mlsanity.com/paper/2308.06101/) (2023)
- [Improving Diffusion Models for Authentic Virtual Try-on in the Wild](https://mlsanity.com/paper/2403.05139/) (2024)
- [CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models](https://mlsanity.com/paper/2407.15886/) (2024)
- [GIM: Learning Generalizable Image Matcher From Internet Videos](https://mlsanity.com/paper/2402.11095/) (2024)
- [Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks](https://mlsanity.com/paper/2501.15891/) (2025)
- [ControlVAR: Exploring Controllable Visual Autoregressive Modeling](https://mlsanity.com/paper/2406.09750/) (2024)

## Abstract (arXiv)

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× 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.