arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.06186cs.CV
收藏

PTDiffusion:利用相位转移扩散模型生成视错觉隐藏图像的免费午餐

PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model

Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所)

Xiang Gao, Shuai Yang, Jiaying Liu

AI总结:

提出无训练文本引导I2I框架PTDiffusion,通过相位转移机制将参考图像嵌入文本描述场景生成视错觉隐藏图像,无需训练微调且在多指标上优于现有方法。

摘要:

视错觉隐藏图像是一种有趣的视觉感知现象,其中一幅图像以观众无法立即察觉的方式巧妙地融入另一幅图像中。基于现成的文本到图像(T2I)扩散模型,我们提出了一种名为**相位转移扩散模型(PTDiffusion)**的新型无训练文本引导图像到图像(I2I)转换框架,用于隐藏艺术合成。PTDiffusion将输入参考图像和谐地嵌入文本提示描述的任意场景中,生成呈现参考图像隐藏视觉线索的错觉图像。我们方法的核心是即插即用的相位转移机制,该机制动态且逐步地将去噪过程中扩散特征的相位谱移植到生成的错觉图像中,实现参考结构信息与文本语义信息在扩散模型潜在空间的深度融合。此外,我们提出异步相位转移,以灵活控制隐藏内容的可辨识度。大量定性和定量实验表明,我们的方法无需任何模型训练和微调过程,同时在错觉图像合成的图像生成质量、文本保真度、视觉可辨识度和上下文自然度方面显著优于相关文本引导I2I方法。我们的项目公开于该网页。

英文摘要:

Optical illusion hidden picture is an interesting visual perceptual phenomenon where an image is cleverly integrated into another picture in a way that is not immediately obvious to the viewer. Established on the off-the-shelf text-to-image (T2I) diffusion model, we propose a novel training-free text-guided image-to-image (I2I) translation framework dubbed as \textbf{P}hase-\textbf{T}ransferred \textbf{Diffusion} Model (PTDiffusion) for hidden art syntheses. PTDiffusion harmoniously embeds an input reference image into arbitrary scenes described by the text prompts, producing illusion images exhibiting hidden visual cues of the reference image. At the heart of our method is a plug-and-play phase transfer mechanism that dynamically and progressively transplants diffusion features' phase spectrum from the denoising process to reconstruct the reference image into the one to sample the generated illusion image, realizing deep fusion of the reference structural information and the textual semantic information in the diffusion model latent space. Furthermore, we propose asynchronous phase transfer to enable flexible control to the degree of hidden content discernability. Our method bypasses any model training and fine-tuning process, all while substantially outperforming related text-guided I2I methods in image generation quality, text fidelity, visual discernibility, and contextual naturalness for illusion picture synthesis, as demonstrated by extensive qualitative and quantitative experiments. Our project is publically available at \href{https://xianggao1102.github.io/PTDiffusion_webpage/}{this web page}.

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。

↑