Advanced image tampering techniques are increasingly challenging the trustworthiness of multimedia, leading to the development of Image Manipulation Localization (IML). But what makes a good IML model? The answer lies in the way to capture artifacts. Exploiting artifacts requires the model to extract non-semantic discrepancies between manipulated and authentic regions, necessitating explicit comparisons between the two areas. With the self-attention mechanism, naturally, the Transformer should be a better candidate to capture artifacts. However, due to limited datasets, there is currently no pure ViT-based approach for IML to serve as a benchmark, and CNNs dominate the entire task. Nevertheless, CNNs suffer from weak long-range and non-semantic modeling. To bridge this gap, based on the fact that artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision that could converge with a small amount of data. We term this simple but effective ViT paradigm IML-ViT, which has significant potential to become a new benchmark for IML. Extensive experiments on five benchmark datasets verified our model outperforms the state-of-the-art manipulation localization methods.Code and models are available at \url{https://github.com/SunnyHaze/IML-ViT}.

翻译：先进的图像篡改技术日益挑战多媒体的可信度，促使图像篡改定位（IML）领域的发展。但何为优秀的IML模型？答案在于捕获伪迹的方式。利用伪迹要求模型提取篡改区域与真实区域之间的非语义差异，这需要显式对比两个区域。借助自注意力机制，Transformer自然成为更优的伪迹捕获候选。然而，受限于有限的数据集，目前尚无纯ViT方法可作为IML基准，CNN仍主导该任务。但CNN存在长程与非语义建模能力薄弱的问题。为弥补这一差距，基于伪迹对图像分辨率敏感、在多尺度特征下被放大、且在篡改边界处密集分布的特性，我们将前述问题的答案表述为：构建一种具备高分辨率能力、多尺度特征提取能力、且能在少量数据下收敛的篡改边缘监督ViT。我们将这一简单而有效的ViT范式命名为IML-ViT，它具备成为IML新基准的巨大潜力。在五个基准数据集上的大量实验验证了我们的模型优于现有最先进的篡改定位方法。代码和模型已开源至\url{https://github.com/SunnyHaze/IML-ViT}。