Abstract
Semantic image synthesis models suffer from training instabilities and poor image quality when trained with adversarial supervision alone. Historically, this was alleviated via an additional VGG-based perceptual loss. Hence, we propose a new simplified GAN model, which needs only adversarial supervision to achieve high-quality results. In doing so, we also show that the VGG supervision decreases image diversity and can hurt image quality. We achieve the improvement by re-designing the discriminator as a semantic segmentation network. The resulting stronger supervision makes the VGG loss obsolete. Moreover, in contrast to previous work, we enable high-quality multi-modal image synthesis through a novel noise sampling scheme. Compared to the state of the art, we achieve an average improvement of 6 FID and 7 mIoU.
V. Sushko and E. Schönfeld—Equal Contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Caesar, H., Uijlings, J., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)
Liu, X., Yin, G., Shao, J., Wang, X., et al.: Learning to predict layout-to-image conditional convolutions for semantic image synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)
Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: Asilomar Conference on Signals, Systems and Computers (2003)
Yazici, Y., Foo, C.S., Winkler, S., Yap, K.H., Piliouras, G., Chandrasekhar, V.: The unusual effectiveness of averaging in GAN training. arXiv preprint arXiv:1806.04498 (2018)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Sushko, V., Schönfeld, E., Zhang, D., Gall, J., Schiele, B., Khoreva, A. (2020). 3D Noise and Adversarial Supervision Is All You Need for Multi-modal Semantic Image Synthesis. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12540. Springer, Cham. https://doi.org/10.1007/978-3-030-65414-6_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-65414-6_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65413-9
Online ISBN: 978-3-030-65414-6
eBook Packages: Computer ScienceComputer Science (R0)