Controllable image generation based on causal representation learning  

作　　者：Shanshan HUANG Yuanhao WANG Zhili GONG Jun LIAO Shu WANG Li LIU 

机构地区：[1]School of Big Data and Software Engineering,Chongqing University,Chongqing 401331,China [2]School of Materials and Energy,Southwest University,Chongqing 400715,China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2024年第1期135-148,共14页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Major Science and Technology Projects of China(No.2022YFB3303302);the National Natural Science Foundation of China(Nos.61977012 and 62207007);the Central Universities Project in China at Chongqing University(Nos.2021CDJYGRH011 and 2020CDJSK06PT14)。

摘　　要：Artificial intelligence generated content(AIGC)has emerged as an indispensable tool for producing large-scale content in various forms,such as images,thanks to the significant role that AI plays in imitation and production.However,interpretability and controllability remain challenges.Existing AI methods often face challenges in producing images that are both flexible and controllable while considering causal relationships within the images.To address this issue,we have developed a novel method for causal controllable image generation(CCIG)that combines causal representation learning with bi-directional generative adversarial networks(GANs).This approach enables humans to control image attributes while considering the rationality and interpretability of the generated images and also allows for the generation of counterfactual images.The key of our approach,CCIG,lies in the use of a causal structure learning module to learn the causal relationships between image attributes and joint optimization with the encoder,generator,and joint discriminator in the image generation module.By doing so,we can learn causal representations in image’s latent space and use causal intervention operations to control image generation.We conduct extensive experiments on a real-world dataset,CelebA.The experimental results illustrate the effectiveness of CCIG.

关 键 词：Image generation Controllable image editing Causal structure learning Causal representation learning 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]