研究人员开发了FitVTON，这是一种新的虚拟试穿模型，它优先考虑逼真的服装合身度，而不是仅仅保留纹理。与将试穿视为二维图像修复的先前方法不同，FitVTON通过结构化文本提示编码服装和身体尺寸信息，并从模拟数据中学习。该模型包括用于预测服装和身体掩码的辅助头，以及用于增强逼真度的纹理校正阶段。实验表明，与现有的最先进方法相比，FitVTON在合身保真度、尺寸准确性和形状保持方面均表现出色。 AI
影响 通过关注准确的服装合身度和尺寸，增强了虚拟试穿应用的逼真度。
排序理由 该集群包含一篇描述新模型和数据集的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.12012v1 Announce Type: new Abstract: While diffusion-based virtual try-on has achieved impressive visual realism, most methods treat the task as 2D inpainting, prioritizing texture preservation over physical plausibility. Consequently, they often produce plausible-look…
While diffusion-based virtual try-on has achieved impressive visual realism, most methods treat the task as 2D inpainting, prioritizing texture preservation over physical plausibility. Consequently, they often produce plausible-looking images that fail to reflect authentic garmen…