A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple objects is understudied. While some frameworks produce high-quality street scenes with little to no control over the image content, others offer more control at the expense of high-quality generation. A common limitation of both approaches is the use of global latent codes for the whole image, which hinders the learning of independent object distributions. Motivated by SemanticStyleGAN (SSG), a recent work on latent space disentanglement in human face generation, we propose a novel framework, Urban-StyleGAN, for urban scene generation and manipulation. We find that a straightforward application of SSG leads to poor results because urban scenes are more complex than human faces. To provide a more compact yet disentangled latent representation, we develop a class grouping strategy wherein individual classes are grouped into super-classes. Moreover, we employ an unsupervised latent exploration algorithm in the $\mathcal{S}$-space of the generator and show that it is more efficient than the conventional ${\mathcal{W}^ + }$-space in controlling the image content. Results on the Cityscapes and Mapillary datasets show the proposed approach achieves significantly more controllability and improved image quality than previous approaches on urban scenes and is on par with general-purpose non-controllable generative models (like StyleGAN2) in terms of quality.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes


    Beteiligte:
    Eskandar, George (Autor:in) / Farag, Youssef (Autor:in) / Yenamandra, Tarun (Autor:in) / Cremers, Daniel (Autor:in) / Guirguis, Karim (Autor:in) / Yang, Bin (Autor:in)


    Erscheinungsdatum :

    2023-06-04


    Format / Umfang :

    3981620 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Counting vehicles in urban traffic scenes using foreground time-spatial images

    Zhang, Yunsheng / Zhao, Chihang / Zhang, Qiuge | IET | 2017

    Freier Zugriff

    Counting vehicles in urban traffic scenes using foreground time‐spatial images

    Zhang, Yunsheng / Zhao, Chihang / Zhang, Qiuge | Wiley | 2017

    Freier Zugriff

    Towards Automatic 3D Reconstruction of Urban Scenes from Low-Altitude Aerial Images

    Huguet, A. / Carceroni, R. / Araujo, A. et al. | British Library Conference Proceedings | 2003


    Towards automatic 3D reconstruction of urban scenes from low-altitude aerial images

    Huguet, A.B. / Carceroni, R.L. / Araujo, A.A. | IEEE | 2003


    Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning

    Itkina, Masha / Driggs-Campbell, Katherine / Kochenderfer, Mykel J. | IEEE | 2019