论文标题
魔术：通过反转准式分类器来构成面具引导的图像综合
MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier
论文作者
论文摘要
我们提供了一种单发掩模引导的图像合成的方法，该方法可以通过反转配备有强正规化器的准稳定分类器来控制单个图像的操作。我们提出的标题为“魔术”的方法利用了预先训练的准稳定分类器的结构化梯度，以更好地保留输入语义，同时保留其分类精度，从而确保合成中的信誉。与当前使用复杂原语监督过程或使用注意图作为弱监督信号的当前方法不同，魔术汇总了输入上的梯度，该梯度是由导向二进制掩码驱动的，该指南二进制掩码执行了强大的空间先验。魔术在一个框架中实现了一系列的操作，以实现形状和位置控制，强烈的非刚性形状变形，并在存在重复对象的情况下复制/移动操作，并通过简单地指定二进制指南蒙版来使用户对综合的企业控制。我们的研究和发现得到了与最先进的图像在ImageNet和使用机器知觉进行定量分析的相同图像上的各种定性比较以及对100多名参与者的用户调查，以认可我们的合成质量。 https://mozhdehrouhsedaghat.github.io/magic.html的项目页面。代码可从https://github.com/mozhdehrouhsedaghat/magic获得
We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers. Our proposed method, entitled MAGIC, leverages structured gradients from a pre-trained quasi-robust classifier to better preserve the input semantics while preserving its classification accuracy, thereby guaranteeing credibility in the synthesis. Unlike current methods that use complex primitives to supervise the process or use attention maps as a weak supervisory signal, MAGIC aggregates gradients over the input, driven by a guide binary mask that enforces a strong, spatial prior. MAGIC implements a series of manipulations with a single framework achieving shape and location control, intense non-rigid shape deformations, and copy/move operations in the presence of repeating objects and gives users firm control over the synthesis by requiring to simply specify binary guide masks. Our study and findings are supported by various qualitative comparisons with the state-of-the-art on the same images sampled from ImageNet and quantitative analysis using machine perception along with a user survey of 100+ participants that endorse our synthesis quality. Project page at https://mozhdehrouhsedaghat.github.io/magic.html. Code is available at https://github.com/mozhdehrouhsedaghat/magic
