arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.08461cs.CV
收藏

Style-Editor:文本驱动的以对象为中心的样式编辑

Style-Editor: Text-driven object-centric style editing

DGIST(大邱庆北科学技术院)

Jihun Park, Jongmin Gim, Kyoungmin Lee, Seunghun Lee, Sunghoon Im

AI总结:

本文提出 Style-Editor,通过逐块同向损失、文本匹配块选择与预固定区域选择模块及自适应背景保持损失,实现无需分割掩码的文本驱动对象级样式编辑。

摘要:

我们提出了一种名为 Style-Editor 的文本驱动的以对象为中心的样式编辑模型,这是一种利用文本输入在以对象为中心层面上引导样式编辑的新方法。Style-Editor 的核心是我们精心设计的逐块同向(PCD)损失,用于实现与输入文本紧密对齐的精确以对象为中心的编辑。该损失结合了用于文本引导样式方向的逐块方向损失和用于在对象区域上均匀分布 CLIP 嵌入的逐块分布一致性损失,确保在对象区域之间实现无缝且和谐的样式编辑。我们方法的关键是文本匹配块选择(TMPS)和预固定区域选择(PRS)模块,它们通过文本识别对象位置,从而无需分割掩码。最后,我们引入了自适应背景保持(ABP)损失,以保持图像背景的原始样式和结构本质。该损失应用于动态识别的背景区域。大量实验突显了我们的方法在创建视觉连贯且与文本对齐的样式编辑方面的有效性。

英文摘要:

We present Text-driven object-centric style editing model named Style-Editor, a novel method that guides style editing at an object-centric level using textual inputs. The core of Style-Editor is our Patch-wise Co-Directional (PCD) loss, meticulously designed for precise object-centric editing that are closely aligned with the input text. This loss combines a patch directional loss for text-guided style direction and a patch distribution consistency loss for even CLIP embedding distribution across object regions. It ensures a seamless and harmonious style editing across object regions. Key to our method are the Text-Matched Patch Selection (TMPS) and Pre-fixed Region Selection (PRS) modules for identifying object locations via text, eliminating the need for segmentation masks. Lastly, we introduce an Adaptive Background Preservation (ABP) loss to maintain the original style and structural essence of the image's background. This loss is applied to dynamically identified background areas. Extensive experiments underline the effectiveness of our approach in creating visually coherent and textually aligned style editing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑