Intelligent vehicle perception algorithms often have difficulty accurately analyzing and interpreting images in adverse weather conditions. Snow is a corner case that not only reduces visibility and contrast but also affects the stability of the road environment. While it is possible to train deep learning models on real-world driving datasets in snow weather, obtaining such data can be challenging. Synthesizing snow effects on existing driving datasets is a viable alternative. In this work, we propose a method based on Cycle Consistent Generative Adversarial Networks (CycleGANs) that utilizes additional semantic information to generate snow effects. We apply deep supervision by using intermediate outputs from the last two convolutional layers in the generator as multi-scale supervision signals for training. We collect a small set of driving image data captured under heavy snow as the translation source. We compare the generated images with those produced by various network architectures and evaluate the results qualitatively and quantitatively on the Cityscapes and EuroCity Persons datasets. Experiment results indicate that our model can synthesize realistic snow effects in driving images.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Synthesizing Realistic Snow Effects in Driving Images Using GANs and Real Data with Semantic Guidance*


    Beteiligte:
    Yang, Hanting (Autor:in) / Ding, Ming (Autor:in) / Carballo, Alexander (Autor:in) / Zhang, Yuxiao (Autor:in) / Ohtani, Kento (Autor:in) / Niu, Yinjie (Autor:in) / Ge, Maoning (Autor:in) / Feng, Yan (Autor:in) / Takeda, Kazuya (Autor:in)


    Erscheinungsdatum :

    04.06.2023


    Format / Umfang :

    1737387 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LiDAR Point Cloud Translation Between Snow and Clear Conditions Using Depth Images and GANs

    Zhang, Yuxiao / Ding, Ming / Yang, Hanting et al. | IEEE | 2023


    Synthesizing Realistic Trajectory Data With Differential Privacy

    Sun, Xinyue / Ye, Qingqing / Hu, Haibo et al. | IEEE | 2023


    Semantic Image Segmentation on Snow Driving Scenarios

    Lei, Yayun / Emaru, Takanori / Ravankar, Ankit A. et al. | British Library Conference Proceedings | 2020


    Flooded Road Detection from Driving Recorder: Training Deep Net for Rare Event Using GANs Semantic Information

    Nakamura, Sho / Ono, Shintaro / Kawasaki, Hiroshi | Springer Verlag | 2021


    Simulating Photo-realistic Snow and Fog on Existing Images for Enhanced CNN Training and Evaluation

    Bernuth, Alexander von / Volk, Georg / Bringmann, Oliver | IEEE | 2019