Lune

ICML2025顶会

WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models

Songbai Tan, Xuerui Qiu, Yao Shu, Gang Xu, Linrui Xu, Xiangyu Xu, Huiping Zhuang, Ming Li, Fei Richard Yu

出版方
2025年份
4顶会引用

摘要

WMarkGPT WMarkGPT: The watermark in the image is centrally oriented, covering a significant portion of the scene. It partially overlaps with the vase and the potted plant, extending across their surfaces and coming close to their edges. The watermark appears as a circular or patterned texture with a moderately visible presence, blending somewhat with the image's elements without being overly intrusive. The watermark visibility is: moderate. The watermark visibility is: <level>. level weight Invisible 9.32e-5 Faint 1.42e-4 Moderate 7.61e-1 Visible 1.87e-1 Obvious 5.22e-2 Score: 2.71 Weight avg.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper4

问问它们各自怎么用它

它引用的顶会 Paper17

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖