Gen-ai 简明教程
Generative Adversarial Networks Applications
生成对抗网络 (GAN) 可以在各种领域生成高度逼真的数据样本，因此它们在生成式建模中引起了极大关注。
Generative Adversarial Networks (GANs) can generate highly realistic data samples across various domains, so they gained significant attention in generative modeling.
GAN 是一种深度学习架构，可以生成高度逼真的数据，难以与实际数据相区分。因此，GAN 用于包括图像生成本身、卡通人物生成本身、3D 对象生成本身和视频预测在内的各种应用中。
GANs are a type of deep learning architecture that can generate highly realistic data which is difficult to distinguish from real data. That’s the reason GANs are used in various applications including image generation, cartoon characters generation, generation of 3D objects, and video prediction.
Applications of Generative Adversarial Networks
阅读本章以清晰了解 GAN 可以解决的问题类型以及广泛使用的领域。
Read this chapter to get a clear understanding of the types of problems that GANs can address and the domains where they are widely used.
Generating Example for Image Dataset
GAN 可以用于生成难以与真实数据区分的合成图像。此应用程序在获取大量真实数据很昂贵或困难的情况下很有用。
GANs can be used to generate synthetic images which are difficult to distinguish from real data. This application is useful in cases where it is either expensive or difficult to get a large amount of real data.
研究人员可以使用合成数据来扩充数据集并训练机器学习模型。它增强了机器学习在各种任务（如分类、分割和对象检测）中的性能。
Researchers can augment datasets with synthetic data and train ML models. It enhances the performance of ML models in various tasks such as classification, segmentation, and object detection.
Generating Photographs of Human Faces
GAN 可以生成非常逼真的人像，包括现实世界中甚至不存在的人像，具有不同年龄、背景和表情等各种特征。我们可以在创建社交媒体头像、生成面部识别系统的训练数据等方面使用这些生成的面孔。
GANs can generate highly realistic photographs of human faces, including those that don’t even exist in the real world, with various characteristics like different ages, backgrounds, and expressions. We can use these generated faces in creating avatars for social media, generating training data for facial recognition system, etc.
例如，我们有一个工具 Generated Photos ，它使用真实和合成数据集通过 AI 从头开始生成人像。以下是一个根据左侧提供的描述由该工具生成的照片示例。
For example, we have a tool Generated Photos that uses real-life and synthetic datasets for generating human photos from scratch by AI. Below is an example of photo generated by this tool based on the description provided in left side.
Generating Realistic Images
GAN 可以生成高度逼真的物体、场景等图像。我们可以在虚拟现实 (VR)、游戏和内容创建等各种领域中使用这些生成的图像。例如，在建筑和室内设计中，建筑师可以使用 GAN 来生成建筑物和内部结构的逼真可视化。
GANs can generate highly realistic images of objects, scenes, etc. We can use these generated images in various domains like virtual reality (VR), gaming, and content creation. For example, in architecture and interior design, architects can use GANs to generate realistic visualizations of buildings and interiors.
DALL.E 3 就是这样的一个工具，它是由 OpenAI 开发的。它是一款由 AI 驱动的图像创建器，改变了建筑师生成视觉效果和扩展其设计的方式。
One such tool is DALL.E 3 which is developed by OpenAI. It is an AI-powered image creator that changes the way architects generate visuals and scale their designs.
Generating Cartoon Characters
艺术家和动画师可以使用 GAN 生成具有不同风格和特征的卡通风格图像。这些生成的卡通图像可用于动画、漫画和角色设计。例如，我们有用于生成卡通人物的工具 Toonify 。
Artists and animators can use GANs to generate cartoon style images with different styes and characteristics. These generated cartoon images can be used in animation, comics, and character design. For example, we have the tool Toonify for generating cartoon characters.
Image-to-Image Translation
GAN，特别是条件 GAN，最适合将图像从一个域翻译到另一个域的任务。翻译图像包括将卫星图像转换为地图、将草图转换为逼真的图像或将白天场景转换为夜景等。例如， Kapwing.com 为我们提供了一个 AI 图像翻译工具。
GANs, specifically Conditional GANs, are best suited for tasks like translating images from one domain to another. Translating images includes converting satellite images to maps, transforming sketches into realistic images, or converting day-time scenes to night-time scenes etc. For example, Kapwing.com provides us an AI image translator tool.
Semantic-Image-to-Realistic Image Translation
GAN 可以根据文本描述或语义布局生成逼真的图像。例如，如果你提供房间的语义布局，GAN 可以生成该房间的逼真照片。这种技术在建筑可视化和室内设计领域很有用。
GANs can generate realistic images based on textual descriptions or semantic layouts. For example, if you provide a semantic layout of a room, GANs can generate a photorealistic image of that room. This technique is useful in the field of architectural visualization and interior design.
Generating Face Frontal View
GAN 可以从非正面图像生成正面面视图。此应用程序在面部识别系统中很有用。例如， Picsart 是一个流行的工具，可用于生成 AI 面孔。
GANs can generate frontal views of faces from non-frontal images. This application is useful in face recognition systems. For example, Picsart is a popular tool that you can use for generating AI faces.
Generating New Poses
GAN，特别是 StyelGAN，可以生成新的人的姿势。此技术在动画、体育分析和虚拟试用应用程序中找到了最好的应用。例如，在体育分析中，GAN 可用于为运动员生成逼真的姿势，以分析他们的动作和技术。
GANs, specifically StyelGANs, can generate new human poses. This technique finds its best application in animation, sports analytics, and virtual try-on applications. For example, in sports analytics, GANs can be used to generate realistic poses for athletes to analyze their movements and techniques.
Generating Emojis from Photos
GAN 可以从你提供给它的照片创建个性化的表情符号风格的图像。这有助于通过自定义视觉表达方式来增强通信平台。例如，你可以使用 “magickimg.com” 从照片中生成表情符号。
GANs can create personalized emojis-style images from the photographs you provided to it. This helps enhance the communication platforms with custom visual expressions. For example, you can use "magickimg.com" to generate emojis from photos.
Image Super-Resolution
GAN 可用于图像超分辨率任务，其中低分辨率图像被转换为类似的高分辨率图像。
GANs can be used for image super-resolution tasks in which low-resolution images are transformed into similar high-resolution images.
Image Inpainting using GAN
基于上下文信息，GAN 可以填充图像中缺失的部分。例如，使用 GAN 的图像修复技术可以重建照片中损坏的区域，这有助于在法医学调查或历史文件保存中恢复有价值的视觉信息。 Fotor.com 为我们提供了一个用于图像修复的 AI 工具。
Based on contextual information, GANs can fill in missing parts of the images. For example, image inpainting techniques using GANs can reconstruct damaged areas in photographs that helps in the recovery of valuable visual information in forensic investigations or in historical document preservation. Fotor.com provides us an AI tool for image inpainting.
Video Prediction using GAN
基于视频中过去帧的给定序列，GAN 可以生成视频序列中逼真的未来帧。这有助于减少存储和传输视频所需的数据量。此技术对于娱乐和虚拟现实应用程序非常有用。
Based on a given sequence of past frames in a video, GANs can generate realistic future frames in a video sequence. This helps in reducing the amount of data required to store and transmit videos. This technique is very useful for entertainment and virtual reality applications.
Generating 3D Objects using GAN
GAN 可以根据对象的 2D 图像生成逼真、高质量的 3D 模型，例如建筑物、汽车和人。我们可以在虚拟现实、视频游戏和计算机辅助设计 (CAD) 中使用它。我们有一个工具 Meshy 可以生成 3D 对象。
GANs can generate realistic, high-quality 3D models of objects like buildings, cars, and people from their 2D images. We can use this in virtual reality, video games, and computer-aided design (CAD). We have a tool Meshy which can generate 3D objects.
Clothing Translation
GAN 已被用于开发服装翻译系统，该系统将服装图像从一种设计转换为另一种设计。名为 Resleeve 的工具可用于此应用程序。它还提供免费试用。
GANs have been used to develop systems for clothing translation which converts an image of clothing from one design to another. The tool named Resleeve can be used for this application. It also gives you a free trial.
Face Morphing
GAN 为我们提供了不同面部属性之间的平滑变形。此功能使 GAN 对诸如年龄进展、性别转换和面部表情转换之类的应用程序很有用。例如， Toonify 也可用于面部变形。
GANs provide us with smooth morphing between different facial attributes. This feature makes GAN useful for applications like age progression, gender transformation, and facial expression transfer. For example, Toonify can also be used for face morphing.
Conclusion
本章探讨的生成对抗网络 (GANs) 的应用程序展示了这项尖端技术在各个领域的非凡潜力。
The applications of Generative Adversarial Networks (GANs) explored in this chapter demonstrate the remarkable potential of this cutting-edge technology across various domains.
GANs 为图像到图像转换、生成新姿势和语义图像到真实照片转换提供了创新方法。
GANs provide innovative approaches to image-to-image translation, generating new poses, and semantic-image-to-realistic photo translation.
从生成人脸的逼真图像到提高照片分辨率，再到为时尚行业提供虚拟试穿体验，GANs 改变了我们创建、处理和与视觉内容互动的方式。
From generating realistic images of human faces to enhancing the resolution of photographs and enabling virtual try-on experiences in the fashion industry, GANs have changed the way we create, manipulate, and interact with visual content.