Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.08147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915846084886528 |
|---|---|
| author | Laczkó, Hunor Jia, Libang Truong, Loc-Phat Hernández, Diego Escalera, Sergio Gonzalez, Jordi Madadi, Meysam |
| author_facet | Laczkó, Hunor Jia, Libang Truong, Loc-Phat Hernández, Diego Escalera, Sergio Gonzalez, Jordi Madadi, Meysam |
| contents | Existing 4D human datasets fall short for fashion-specific research, lacking either realistic garment dynamics or task-specific annotations. Synthetic datasets suffer from a realism gap, whereas real-world captures lack the detailed annotations and paired data required for virtual try-on (VTON) and size estimation tasks. To bridge this gap, we introduce MV-Fashion, a large-scale, multi-view video dataset engineered for domain-specific fashion analysis. MV-Fashion features 3,273 sequences (72.5 million frames) from 80 diverse subjects wearing 3-10 outfits each. It is designed to capture complex, real-world garment dynamics, including multiple layers and varied styling (e.g. rolled sleeves, tucked shirt). A core contribution is a rich data representation that includes pixel-level semantic annotations, ground-truth material properties like elasticity, and 3D point clouds. Crucially for VTON applications, MV-Fashion provides paired data: multi-view synchronized captures of worn garments alongside their corresponding flat, catalogue images. We leverage this dataset to establish baselines for fashion-centric tasks, including virtual try-on, clothing size estimation, and novel view synthesis. The dataset is available at https://hunorlaczko.github.io/MV-Fashion . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08147 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data Laczkó, Hunor Jia, Libang Truong, Loc-Phat Hernández, Diego Escalera, Sergio Gonzalez, Jordi Madadi, Meysam Computer Vision and Pattern Recognition Existing 4D human datasets fall short for fashion-specific research, lacking either realistic garment dynamics or task-specific annotations. Synthetic datasets suffer from a realism gap, whereas real-world captures lack the detailed annotations and paired data required for virtual try-on (VTON) and size estimation tasks. To bridge this gap, we introduce MV-Fashion, a large-scale, multi-view video dataset engineered for domain-specific fashion analysis. MV-Fashion features 3,273 sequences (72.5 million frames) from 80 diverse subjects wearing 3-10 outfits each. It is designed to capture complex, real-world garment dynamics, including multiple layers and varied styling (e.g. rolled sleeves, tucked shirt). A core contribution is a rich data representation that includes pixel-level semantic annotations, ground-truth material properties like elasticity, and 3D point clouds. Crucially for VTON applications, MV-Fashion provides paired data: multi-view synchronized captures of worn garments alongside their corresponding flat, catalogue images. We leverage this dataset to establish baselines for fashion-centric tasks, including virtual try-on, clothing size estimation, and novel view synthesis. The dataset is available at https://hunorlaczko.github.io/MV-Fashion . |
| title | MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.08147 |