无需训练即可精准迁移图像，自动识别并保留关键区域。
Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking
- 动态调整二值掩码，基于预测差异自适应生成时间相关阈值。
- 在AFHQ和Celeba-HQ上实现更真实（FID/KID更低）且更忠实（SSIM/LPIPS更优）的图像翻译。
- 仅需目标域预训练模型，适用于任意源图像分布，适合自动化图像编辑场景。
本文提出一种无需源数据训练的图像翻译框架，通过计算预训练扩散模型在每个潜在时间步的预测差异，动态优化二值掩码。不同于固定阈值，该方法基于目标分布中噪声潜变量的预测差异的均值与标准差，构建随时间变化的统计阈值，使掩码能适应模型在不同噪声水平下的预测置信度，有效隔离域特定区域同时保持全局结构一致性。在AFHQ和Celeba-HQ数据集上的实验表明，该方法在无监督图像到图像转换任务中，于真实度（FID、KID）与忠实度（SSIM、LPIPS）方面均优于当前最优方法。仅需目标域预训练模型，即可实现跨多种源分布的精确、自动区域定位与无缝翻译。项目代码已公开于：https://github.com/dtoma95/PM-Edit
原文摘要 · Abstract (English)
In this work, we propose a source-agnostic framework that dynamically refines a binary mask throughout the reverse diffusion process by computing the discrepancies of a pretrained diffusion model's prediction for each latent time step. Rather than relying on a fixed threshold, our method introduces a time-dependent statistical thresholding scheme derived from the empirical mean and standard deviation of prediction discrepancies across the latent noisy images from the target distribution. This allows the mask to adapt to the model's varying predictive confidence at different noise levels, effectively isolating domain-specific regions while preserving global structural coherence. Experimental results on the AFHQ and Celeba-HQ datasets demonstrate that our approach outperforms state-of-the-art unsupervised Image-to-Image methods in both realism (FID, KID) and faithfulness (SSIM, LPIPS). By requiring only a pretrained model of the target domain, our approach enables precise, automated localization and seamless translation across diverse source distributions without any specialized training. The project source code is available at: https://github.com/dtoma95/PM-Edit
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。