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正日益挑战多媒体的可信度，由此催生了图像篡改定位（IML）研究的发展。但何种因素决定了优秀IML模型的表现？答案在于伪影捕获的方式。利用伪影要求模型提取篡改区域与真实区域之间的非语义差异，这需要两类区域间的显式比较。凭借自注意力机制，Transformer自然成为更优的伪影捕获候选方案。然而，受限于数据集规模，目前尚无纯ViT架构的IML基准方法，卷积神经网络（CNN）仍主导该领域任务。但CNN在长距离建模与非语义建模方面存在明显不足。为弥补这一差距，基于伪影对图像分辨率敏感、在多尺度特征下放大、且在篡改边界处密集分布的特性，我们提出构建具有高分辨率能力、多尺度特征提取能力、且能通过少量数据收敛的篡改边缘监督ViT模型。我们将这一简洁高效的ViT范式命名为IML-ViT，其具备成为IML新基准的巨大潜力。在五个基准数据集上的大量实验证明，我们的模型性能超越了当前最先进的篡改定位方法。代码与模型已开源发布于：\url{https://github.com/SunnyHaze/IML-ViT}