针对孟加拉传统服饰的虚拟试穿，构建新数据集并验证模型表现
Virtual Try-On for Cultural Clothing: A Benchmarking Study
- 构建面向孟加拉服饰的BD-VITON数据集，涵盖纱丽、衬衫裤等复杂结构
- 在新数据集上重训练模型，定量与定性评估均优于零样本推理
- 为文化多样性服饰试穿提供首个基准，适合跨文化服装研究者
尽管现有虚拟试穿系统借助扩散模型取得显著进展，但当前基准数据集仍以西方服饰和女性模特为主，难以泛化至多元文化服饰。本文提出BD-VITON，一个聚焦孟加拉传统服饰（如纱丽、潘杰布、萨尔瓦卡米兹）的数据集，涵盖男女两类。这些服饰具有复杂的垂坠、不对称叠穿与高形变特性，是原VITON数据集所欠缺的。我们对StableViton、HR-VITON和VITON-HD模型在该数据集上重新训练并评估，实验表明其在量化与质性分析上均显著优于零样本推理。
原文摘要 · Abstract (English)
Although existing virtual try-on systems have made significant progress with the advent of diffusion models, the current benchmarks of these models are based on datasets that are dominant in western-style clothing and female models, limiting their ability to generalize culturally diverse clothing styles. In this work, we introduce BD-VITON, a virtual try-on dataset focused on Bangladeshi garments, including saree, panjabi and salwar kameez, covering both male and female categories as well. These garments present unique structural challenges such as complex draping, asymmetric layering, and high deformation complexities which are underrepresented in the original VITON dataset. To establish strong baselines, we retrain and evaluate try-on models, namely StableViton, HR-VITON, and VITON-HD on our dataset. Our experiments demonstrate consistent improvements in terms of both quantitative and qualitative analysis, compared to zero shot inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。