发布了两个新的大规模数据集GarmentSketch和VietFashion，以推进时尚行业的草图到图像生成和检索。GarmentSketch提供了26,249张时尚草图及其详细的文本描述，旨在改善设计中的人机协作。VietFashion专注于文化服饰，特别是越南奥黛（áo dài），通过超过21,000张图像和匹配的标题，为草图-文本组合图像检索提供了基准。 AI
影响 这些数据集将推动AI驱动的时尚设计工具的进步，改善草图理解和文化特定服装的检索。
排序理由 两篇介绍用于时尚相关AI任务的大规模数据集的学术论文。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2606.14025v1 Announce Type: new Abstract: Fashion sketching is a cornerstone of design workflows, allowing rapid visualization of creative concepts prior to physical prototyping. Yet, progress in sketch-based fashion image synthesis has been hindered by the absence of large…
arXiv:2606.13427v1 Announce Type: new Abstract: Cultural garments pose a unique challenge for visual retrieval systems, as their identity often depends on subtle structural and symbolic details that are poorly captured by standard AI models. We introduce VietFashion, a new benchm…
Fashion sketching is a cornerstone of design workflows, allowing rapid visualization of creative concepts prior to physical prototyping. Yet, progress in sketch-based fashion image synthesis has been hindered by the absence of large-scale, high-quality paired resources. To bridge…
Cultural garments pose a unique challenge for visual retrieval systems, as their identity often depends on subtle structural and symbolic details that are poorly captured by standard AI models. We introduce VietFashion, a new benchmark for sketch-text composed image retrieval cen…