论文标题
通过文本照明油漆的一致性
Lighting (In)consistency of Paint by Text
论文作者
论文摘要
尽管生成的对抗网络能够综合面部，猫，景观或几乎任何其他单一类别的高度逼真的图像，但逐文的油漆综合引擎可以 - 从单个文本提示中 - 合成具有任意配置和组合的看似无尽类别的现实图像。这项强大的技术为照片法医社区带来了新的挑战。通过文本绘画不是基于明确的几何或物理模型，以及人类视觉系统对照明不一致的普遍不敏感的事实，我们提供了对DALL-E-2合成图像的照明一致性的初步探索，以确定基于物理的赋形性分析是否会在检测这种新的合成媒体中效率。
Whereas generative adversarial networks are capable of synthesizing highly realistic images of faces, cats, landscapes, or almost any other single category, paint-by-text synthesis engines can -- from a single text prompt -- synthesize realistic images of seemingly endless categories with arbitrary configurations and combinations. This powerful technology poses new challenges to the photo-forensic community. Motivated by the fact that paint by text is not based on explicit geometric or physical models, and the human visual system's general insensitivity to lighting inconsistencies, we provide an initial exploration of the lighting consistency of DALL-E-2 synthesized images to determine if physics-based forensic analyses will prove fruitful in detecting this new breed of synthetic media.
