arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02897cs.CV
收藏

深度图像合成与图像伪造的交汇

Deep Image Composition Meets Image Forgery

Yildiz Technical University(伊兹密尔技术大学)

Eren Tahir, Mert Bal

AI总结:

本研究提出利用SOTA深度图像合成技术自动生成高质量拼接图像数据集,以解决现有图像伪造检测数据集在规模、真实感和像素级标注上的不足,实验证明该数据集比现有数据集更难被检测。

摘要:

图像伪造是一个被研究了多年的课题。在深度学习取得突破之前,伪造图像是使用不需要训练的手工特征来检测的。这些传统方法即使在质量远差于现实生活图像篡改的数据集上也未能表现令人满意。深度学习的进展在影响计算机视觉其他领域的同时,也影响了图像伪造检测,并提升了现有技术的水平。深度学习模型需要大量标注数据进行训练。在图像伪造的情况下,像素级的标注数据是模型进行学习的一个非常重要的因素。现有的数据集都没有同时具备足够的规模、真实感和像素级标注。这是由于制作和标注高质量图像的成本很高。一位图像编辑专家处理一张图像可能需要数小时。为了弥合这一差距,我们使用与图像伪造非常相关的图像合成技术来自动化数据生成。与其他自动化数据生成框架不同,我们使用SOTA图像合成深度学习模型来生成接近现实生活篡改质量的拼接图像。最后,我们在SOTA图像篡改检测模型上测试了生成的数据集,并表明与现有数据集相比,其预测性能较低,即我们生成了更难检测的逼真图像。数据集将在 https://github.com/99eren99/DIS25k 提供。

英文摘要:

Image forgery is a topic that has been studied for many years. Before the breakthrough of deep learning, forged images were detected using handcrafted features that did not require training. These traditional methods failed to perform satisfactorily even on datasets much worse in quality than real-life image manipulations. Advances in deep learning have impacted image forgery detection as much as they have impacted other areas of computer vision and have improved the state of the art. Deep learning models require large amounts of labeled data for training. In the case of image forgery, labeled data at the pixel level is a very important factor for the models to learn. None of the existing datasets have sufficient size, realism and pixel-level labeling at the same time. This is due to the high cost of producing and labeling quality images. It can take hours for an image editing expert to manipulate just one image. To bridge this gap, we automate data generation using image composition techniques that are very related to image forgery. Unlike other automated data generation frameworks, we use state of the art image composition deep learning models to generate spliced images close to the quality of real-life manipulations. Finally, we test the generated dataset on the SOTA image manipulation detection model and show that its prediction performance is lower compared to existing datasets, i.e. we produce realistic images that are more difficult to detect. Dataset will be available at https://github.com/99eren99/DIS25k .

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。

↑