{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mobilestylegan-a-lightweight-convolutional","title":"MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis","arxiv_id":"2104.04767","date":"2021-04-10","proceeding":null,"authors":["Sergei Belousov"],"abstract":"In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling. While style-based GAN architectures yield state-of-the-art results in high-fidelity image synthesis, computationally, they are highly complex. In our work, we focus on the performance optimization of style-based generative models. We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. We introduce MobileStyleGAN architecture, which has x3.5 fewer parameters and is x9.5 less computationally complex than StyleGAN2, while providing comparable quality.","url_abs":"https://arxiv.org/abs/2104.04767v2","url_pdf":"https://arxiv.org/pdf/2104.04767v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mobilestylegan-a-lightweight-convolutional","repo_url":"https://github.com/bes-dev/MobileStyleGAN.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mobilestylegan-a-lightweight-convolutional","repo_url":"https://github.com/bes-dev/random_face","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mobilestylegan-a-lightweight-convolutional","repo_url":"https://github.com/Harrypotterrrr/MobileStyleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"path-length-regularization","method_name":"Path Length Regularization"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"},{"method_slug":"weight-demodulation","method_name":"Weight Demodulation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.04767","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}