arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2608.05834cs.CV

可控服装:基于潜在扩散模型的虚拟试穿精准标签与生成

Controllable Clothing: Precise Labels and Generation for Virtual Try-On with Latent Diffusion Models

  • Publicis Resources GenAI Team(阳狮集团GenAI团队)
  • École Polytechnique(巴黎综合理工学院)
  • KTH(皇家理工学院)

机构由 AI 辅助整理,请以论文原文为准。

Max Rehman Linder

AI总结:

本研究提出基于潜在扩散模型的新方法,通过开源AI模型添加标签并训练适配器,实现虚拟试穿图像的可控生成,可避免误导消费者。

AI中文摘要:

在本技术报告中,我提出了一种用于指导虚拟试穿(VITON)场景下图像生成的新方法。该方法利用新的开源AI模型为图像数据添加长度、款式等标签进行增强,通过将这些标签与服装图像配对训练适配器,模型可生成用户能控制的更多样化图像。对于零售商等终端用户而言,这意味着他们能确保生成的图像尽可能贴合真实合身度,不会误导消费者。

英文摘要:

In this technical report, I present a new method for guiding image generation in the context of Virtual- Try-On (VITON). The proposed method leverages new open source Ai models to augment the image data with labels, such as lengths and styles. By training adapters with these labels paired with images of the garments, the model can produce a more diverse set of images that the user can control. For the end user, such as a retailer, this means that they can assure that the produced image is as true to the true fit as possible, not misleading consumers

↑