Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.08716 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913020806955008 |
|---|---|
| author | Truong, Loc-Phat Madadi, Meysam Escalera, Sergio |
| author_facet | Truong, Loc-Phat Madadi, Meysam Escalera, Sergio |
| contents | Virtual Try-On (VTON) has seen rapid advancements, providing a strong foundation for generative fashion tasks. However, the inverse problem, Virtual Try-Off (VTOFF)-aimed at reconstructing the canonical garment from a draped-on image-remains a less understood domain, distinct from the heavily researched field of VTON. In this work, we seek to establish a robust architectural foundation for VTOFF by studying and adapting various diffusion-based strategies from VTON and general Latent Diffusion Models (LDMs). We focus our investigation on the Dual-UNet Diffusion Model architecture and analyze three axes of design: (i) Generation Backbone: comparing Stable Diffusion variants; (ii) Conditioning: ablating different mask designs, masked/unmasked inputs for image conditioning, and the utility of high-level semantic features; and (iii) Losses and Training Strategies: evaluating the impact of the auxiliary attention-based loss, perceptual objectives and multi-stage curriculum schedules. Extensive experiments reveal trade-offs across various configuration options. Evaluated on VITON-HD and DressCode datasets, our framework achieves state-of-the-art performance with a drop of 9.5\% on the primary metric DISTS and competitive performance on LPIPS, FID, KID, and SSIM, providing both stronger baselines and insights to guide future Virtual Try-Off research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08716 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction Truong, Loc-Phat Madadi, Meysam Escalera, Sergio Computer Vision and Pattern Recognition Virtual Try-On (VTON) has seen rapid advancements, providing a strong foundation for generative fashion tasks. However, the inverse problem, Virtual Try-Off (VTOFF)-aimed at reconstructing the canonical garment from a draped-on image-remains a less understood domain, distinct from the heavily researched field of VTON. In this work, we seek to establish a robust architectural foundation for VTOFF by studying and adapting various diffusion-based strategies from VTON and general Latent Diffusion Models (LDMs). We focus our investigation on the Dual-UNet Diffusion Model architecture and analyze three axes of design: (i) Generation Backbone: comparing Stable Diffusion variants; (ii) Conditioning: ablating different mask designs, masked/unmasked inputs for image conditioning, and the utility of high-level semantic features; and (iii) Losses and Training Strategies: evaluating the impact of the auxiliary attention-based loss, perceptual objectives and multi-stage curriculum schedules. Extensive experiments reveal trade-offs across various configuration options. Evaluated on VITON-HD and DressCode datasets, our framework achieves state-of-the-art performance with a drop of 9.5\% on the primary metric DISTS and competitive performance on LPIPS, FID, KID, and SSIM, providing both stronger baselines and insights to guide future Virtual Try-Off research. |
| title | What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08716 |