date
type
status
slug
summary
tags
category
icon
password
July 26, 2021 • 2 min read
by Simon's Daydream, mp.weixin.qq.comSee original
In this year’s CDRF 2021 (Tongji Digital Futures 2021 Conference), I presented my paper titled "Architectural Facade Perpetual Motion Machine — Exploring Architectural Design in High-Dimensional Latent Space" (translated title, casually translated to make it sound impressive). This Chinese explanation video explores an AI method capable of generating high-confidence architectural facades and visualizing images in high-dimensional latent space based on their latent vector coordinates, along with performing semantic operations on image content using principal component analysis.
Some advanced mathematics and machine learning concepts will be discussed; feel free to ask me questions if you don’t understand (though I might not be able to explain it any clearer!). I am not from a computer science background, so if there are any mistakes, please feel free to point them out gently!
Demo
Explanation
 
1 Introduction
With the emerging of Generative Adversarial Network (GAN) based image generation methodin recent years, many attempts havebeen made to apply GAN into architectural images and drawing generation research(Goodfellowet al. 2014). However, for therealistic building façade images generation task, most attempts faced different challenges, such as quality and controllability ofgenerated image, and interpretabilityof model.
These challenges were due to various limitations, such as performance ofthe selected GAN model, the size of training dataset, the understanding oflatent space, etc. In this paper, by training the state-of-the-art GAN basedimage generation model, StyleGAN2 (Karras et al. 2020), with high-resolution building façade image dataset, andexploring its latent space by applying PCA and GANSpace analysis, we couldovercome above challenges in different extend (Härkönen et al. 2020).
In summary,the main functions and contributions of this paper are:
1.  A StyleGAN2 model instance which could generate plausible buildingfaçade images without conditional input.
2.  Introduce GANSpace and image embedding method to visualize the correlationbetween the generated building façade images and their corresponding latentvectors, which achievedunsupervised classification and high-level propertiescontrol of both generated and novel images.
相关文章
DreamGaussian: The Stable Diffusion Moment of AIGC 3D Generation
Lazy loaded image
How I Used AI to Create a Promotional Video for Xiaomi's Daniel Arsham Limited Edition Smartphone
Lazy loaded image
3D scene editing has entered the era of AI text interaction
Lazy loaded image
Works Series - Dimensional Recasting
Lazy loaded image
The Basic Principles of ChatGPT
Lazy loaded image
From Hand Modeling to Text Modeling: A Comprehensive Explanation of the Latest AI Algorithms for Generating 3D Models from Text
Lazy loaded image
Using AI to transcend every doomsday of humanity until the end of the universe!How to Create Illusions of Consciousness in Large Language Models? A Close Reading of Stanford AI Town Paper
Loading...
Simon Shengyu Meng
Simon Shengyu Meng
AI artist driven by curiosity, cross-disciplinary researcher, PhD candidate, science communication blogger.
最新发布
Works Series - Boundless Intelligence
Oct 13, 2024
Works Series - RE-Imaginate nature
Oct 8, 2024
Supernova Explosion | Simon Meng | AI Genesis
Oct 5, 2024
At the end of 2023, I want to share two comforting AI tools with you and have a heartfelt chat.
Oct 5, 2024
"Slacking Off" but Accidentally Discovering a New Vision for AI — Interview with GAAC Contestants Wang Zheng and Meng Shengyu
Oct 5, 2024
Using AI to transcend every doomsday of humanity until the end of the universe!
Oct 5, 2024
公告
--- About me ---
--- Contact Me ---
Design and Art Creation | AIGC Consultation and Training | Commercial Deployment