UGD-IML：一种用于约束和无约束图像篡改定位的统一生成式扩散框架
UGD-IML: A Unified Generative Diffusion-based Framework for Constrained and Unconstrained Image Manipulation Localization
AI总结：
提出统一生成式扩散框架UGD-IML，首次同时处理约束与无约束图像篡改定位，降低标注依赖，F1指标分别超越SOTA 9.66和4.36。
摘要：
在数字时代，先进的图像编辑工具对视觉内容的完整性构成严重威胁，使得图像伪造检测与定位成为关键研究焦点。大多数现有的图像篡改定位（IML）方法依赖于判别式学习，并且需要大规模、高质量标注的数据集。然而，当前数据集缺乏足够的规模和多样性，限制了模型在现实场景中的性能。为克服这一问题，近期研究探索了约束式图像篡改定位（CIML），通过算法监督生成像素级标注。然而，现有CIML方法往往依赖复杂的多阶段流水线，导致标注过程效率低下。在本工作中，我们提出了一种基于扩散模型的新型生成式框架，命名为UGD-IML，首次在单一框架内统一了IML和CIML两类任务。通过学习底层数据分布，生成式扩散模型从本质上降低了对大规模标注数据集的依赖，使得我们的方法即使在数据有限的条件下也能有效运行。此外，通过利用类别嵌入机制和参数共享设计，我们的模型无需额外组件或训练开销即可在IML和CIML模式之间无缝切换。更进一步，端到端设计使我们的模型避免了数据标注过程中的繁琐步骤。在多个数据集上的大量实验结果表明，UGD-IML在IML和CIML任务上的F1指标上分别平均超过最先进（SOTA）方法9.66和4.36。此外，所提出的方法在不确定性估计、可视化和鲁棒性方面也表现出色。
英文摘要：
In the digital age, advanced image editing tools pose a serious threat to the integrity of visual content, making image forgery detection and localization a key research focus. Most existing Image Manipulation Localization (IML) methods rely on discriminative learning and require large, high-quality annotated datasets. However, current datasets lack sufficient scale and diversity, limiting model performance in real-world scenarios. To overcome this, recent studies have explored Constrained IML (CIML), which generates pixel-level annotations through algorithmic supervision. However, existing CIML approaches often depend on complex multi-stage pipelines, making the annotation process inefficient. In this work, we propose a novel generative framework based on diffusion models, named UGD-IML, which for the first time unifies both IML and CIML tasks within a single framework. By learning the underlying data distribution, generative diffusion models inherently reduce the reliance on large-scale labeled datasets, allowing our approach to perform effectively even under limited data conditions. In addition, by leveraging a class embedding mechanism and a parameter-sharing design, our model seamlessly switches between IML and CIML modes without extra components or training overhead. Furthermore, the end-to-end design enables our model to avoid cumbersome steps in the data annotation process. Extensive experimental results on multiple datasets demonstrate that UGD-IML outperforms the SOTA methods by an average of 9.66 and 4.36 in terms of F1 metrics for IML and CIML tasks, respectively. Moreover, the proposed method also excels in uncertainty estimation, visualization and robustness.
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。
