MV-Fashion：面向虚拟试穿与尺寸估计的多视角配对数据集
MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data
提供了带配对平铺商品图的多视角同步视频与像素级标注、材质属性、点云，可直接作为虚拟试穿与服装尺寸估计的监督/评测基准，也适合做动态人体新视角合成的真实数据来源。
原文依据 MV-Fashion provides paired data: multi-view synchronized captures of worn garments alongside their corresponding flat, catalogue images.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的4D人体数据集难以满足时尚领域的专门研究，要么缺乏真实的服装动态，要么缺少任务特定的标注。合成数据集存在真实感差距，而真实世界采集则缺乏虚拟试穿（VTON）与尺寸估计任务所需的详细标注和配对数据。为弥合这一差距，我们提出MV-Fashion，一个面向特定领域时尚分析而构建的大规模多视角视频数据集。MV-Fashion包含来自80名不同受试者的3,273段序列（7250万帧），每人穿着3至10套服装。该数据集旨在捕捉复杂的真实服装动态，包括多层穿着与多样造型（如卷起的袖子、塞进裤腰的衬衫）。其核心贡献在于丰富的数据表示，包括像素级语义标注、弹性等真实材质属性以及3D点云。对VTON应用而言尤为关键的是，MV-Fashion提供配对数据：穿着状态服装的多视角同步采集及其对应的平铺商品图。我们利用该数据集建立了面向时尚核心任务的基线，包括虚拟试穿、服装尺寸估计与新视角合成。数据集见 https://hunorlaczko.github.io/MV-Fashion。
英文原文摘要 1274 字符
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.