Image and shape editing are ubiquitous among digital artworks. Graphics algorithms facilitate artists and designers to achieve desired editing intents without going through manually tedious retouching. In the recent advance of machine learning, artists' editing intents can even be driven by text, using a variety of well-trained neural networks. They have seen to be receiving an extensive success on such as generating photorealistic images, artworks and human poses, stylizing meshes from text, or auto-completion given image and shape priors. In this short survey, we provide an overview over 50 papers on state-of-the-art (text-guided) image-and-shape generation techniques. We start with an overview on recent editing algorithms in the introduction. Then, we provide a comprehensive review on text-guided editing techniques for 2D and 3D independently, where each of its sub-section begins with a brief background introduction. We also contextualize editing algorithms under recent implicit neural representations. Finally, we conclude the survey with the discussion over existing methods and potential research ideas.
翻译:图像和形状编辑在数字艺术作品中十分普遍。图形算法激励着艺术家和设计师,以达到所需的编辑目的,而不必经历手动繁琐的修饰过程。在机器学习的最新进展中,艺术家的编辑意图甚至可以通过文本驱动,使用各种已经训练良好的神经网络。它们在生成照片级图像、艺术品和人体姿势、从文本中进行网格样式化或给出图像和形状先验信息的自动完成等方面得到了广泛的成功。在本短篇综述中,我们概述了50篇关于最先进的(文本引导的)图像和形状生成技术的论文。我们从简介中对最近的编辑算法进行概述。然后,我们分别为2D和3D提供了全面的文本引导编辑技术综述,其中每个子部分都以简要的背景介绍开头。我们还将编辑算法置于最近的隐式神经表示下进行了上下文化。最后,我们通过讨论现有的方法和可能的研究思路来总结综述。