Skip to main content

ChunkyGAN: Real Image Inversion via Segments

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13683))

Included in the following conference series:

Abstract

We present ChunkyGAN—a novel paradigm for modeling and editing images using generative adversarial networks. Unlike previous techniques seeking a global latent representation of the input image, our approach subdivides the input image into a set of smaller components (chunks) specified either manually or automatically using a pre-trained segmentation network. For each chunk, the latent code of a generative network is estimated locally with greater accuracy thanks to a smaller number of constraints. Moreover, during the optimization of latent codes, segmentation can further be refined to improve matching quality. This process enables high-quality projection of the original image with spatial disentanglement that previous methods would find challenging to achieve. To demonstrate the advantage of our approach, we evaluated it quantitatively and also qualitatively in various image editing scenarios that benefit from the higher reconstruction quality and local nature of the approach. Our method is flexible enough to manipulate even out-of-domain images that would be hard to reconstruct using global techniques.

A. Šubrtová and D. Futschik—Joint first authors.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Abdal, R., Qin, Y., Wonka, P.: Image2StyleGAN: how to embed images into the StyleGAN latent space? In: Proceedings of IEEE International Conference on Computer Vision (2019)

    Google Scholar 

  2. Abdal, R., Zhu, P., Mitra, N.J., Wonka, P.: StyleFlow: attribute-conditioned exploration of styleGAN-generated images using conditional continuous normalizing flows. ACM Trans. Graph. 40(3), 21 (2021)

    Article  Google Scholar 

  3. Alaluf, Y., Patashnik, O., Cohen-Or, D.: ReStyle: a residual-based StyleGAN encoder via iterative refinement. In: Proceedings of IEEE International Conference on Computer Vision, pp. 6711–6720 (2021)

    Google Scholar 

  4. Alaluf, Y., Tov, O., Mokady, R., Gal, R., Bermano, A.H.: HyperStyle: StyleGAN inversion with hypernetworks for real image editing. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 18511–18521 (2022)

    Google Scholar 

  5. Bau, D., et al.: Seeing what a GAN cannot generate. In: Proceedings of IEEE International Conference on Computer Vision, pp. 4501–4510 (2019)

    Google Scholar 

  6. Deng, J., Guo, J., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4685–4694 (2019)

    Google Scholar 

  7. Dinh, T.M., Tran, A.T., Nguyen, R., Hua, B.S.: HyperInverter: improving styleGAN inversion via hypernetwork. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 11389–11398 (2022)

    Google Scholar 

  8. Fišer, J., et al.: Example-based synthesis of stylized facial animations. ACM Trans. Graph. 36(4), 155 (2017)

    Article  Google Scholar 

  9. Futschik, D., Lukáč, M., Shechtman, E., Sýkora, D.: Real image inversion via segments. In: arXiv. No. 2110.06269 (2021)

    Google Scholar 

  10. Huh, M., Zhang, R., Zhu, J.Y., Paris, S., Hertzmann, A.: Transforming and projecting images into class-conditional generative networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 17–34 (2020)

    Google Scholar 

  11. Kang, K., Kim, S., Cho, S.: GAN inversion for out-of-range images with geometric transformations. In: Proceedings of IEEE International Conference on Computer Vision, pp. 13941–13949 (2021)

    Google Scholar 

  12. Karras, T., et al.: Alias-free generative adversarial networks. In: Proceedings of Conference on Neural Information Processing Systems (2021)

    Google Scholar 

  13. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)

    Google Scholar 

  14. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 8107–8116 (2020)

    Google Scholar 

  15. Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5549–5558 (2020)

    Google Scholar 

  16. Ling, H., Kreis, K., Li, D., Kim, S.W., Torralba, A., Fidler, S.: EditGAN: high-precision semantic image editing. In: Proceedings of Conference on Neural Information Processing Systems (2021)

    Google Scholar 

  17. Lipton, Z.C., Tripathi, S.: Precise recovery of latent vectors from generative adversarial networks. In: Proceedings of International Conference on Learning Representations (2017)

    Google Scholar 

  18. Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2085–2094 (2021)

    Google Scholar 

  19. Pérez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM Trans. Graph. 22(3), 313–318 (2003)

    Article  Google Scholar 

  20. Richardson, E., et al.: Encoding in style: a styleGAN encoder for image-to-image translation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2288–2296 (2021)

    Google Scholar 

  21. Roich, D., Mokady, R., Bermano, A.H., Cohen-Or, D.: Pivotal tuning for latent-based editing of real images. In: arXiv. No. 2106.05744 (2021)

    Google Scholar 

  22. Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for StyleGAN image manipulation. ACM Trans. Graph. 40(4), 133 (2021)

    Article  Google Scholar 

  23. Wu, Z., Lischinski, D., Shechtman, E.: StyleSpace analysis: disentangled controls for StyleGAN image generation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 12863–12872 (2021)

    Google Scholar 

  24. Xu, Y., Du, Y., Xiao, W., Xu, X., He, S.: From continuity to editability: inverting GANs with consecutive images. In: Proceedings of IEEE International Conference on Computer Vision, pp. 13910–13918 (2021)

    Google Scholar 

  25. Yao, X., Newson, A., Gousseau, Y., Hellier, P.: Feature-style encoder for style-based GAN inversion. In: arXiv. No. 2202.02183 (2022)

    Google Scholar 

  26. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–595 (2018)

    Google Scholar 

  27. Zhang, Y., et al.: DatasetGAN: efficient labeled data factory with minimal human effort. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 10145–10155 (2021)

    Google Scholar 

  28. Zhu, J., Shen, Y., Zhao, D., Zhou, B.: In-domain GAN inversion for real image editing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 592–608. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58520-4_35

    Chapter  Google Scholar 

  29. Zhu, J.-Y., Krähenbühl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597–613. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_36

    Chapter  Google Scholar 

  30. Zhu, P., Abdal, R., Femiani, J., Wonka, P.: Barbershop: GAN-based image compositing using segmentation masks. ACM Trans. Graph. 40(6), 215 (2021)

    Article  Google Scholar 

Download references

Acknowledgments

We thank the anonymous reviewers for their valuable feedback and insightful comments. We are also grateful to Jakub Javora for creating some of the interactive editing examples. This research was supported by Adobe, the Grant Agency of the Czech Technical University in Prague, grants No. SGS19/179/OHK3/3T/13 and No. SGS20/171/OHK3/3T/13, and by the Research Center for Informatics, grant No. CZ.02.1.01/0.0/0.0/16_019/0000765.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Daniel Sýkora .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 9972 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Šubrtová, A., Futschik, D., Čech, J., Lukáč, M., Shechtman, E., Sýkora, D. (2022). ChunkyGAN: Real Image Inversion via Segments. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13683. Springer, Cham. https://doi.org/10.1007/978-3-031-20050-2_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20050-2_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20049-6

  • Online ISBN: 978-3-031-20050-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics