Skip to main content

Rayleigh EigenDirections (REDs): Nonlinear GAN Latent Space Traversals for Multidimensional Features

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13677))

Included in the following conference series:

  • 2649 Accesses

Abstract

We present a method for finding paths in a deep generative model’s latent space that can maximally vary one set of image features while holding others constant. Crucially, unlike past traversal approaches, ours can manipulate arbitrary multidimensional features of an image such as facial identity and pixels within a specified region. Our method is principled and conceptually simple: optimal traversal directions are chosen by maximizing differential changes to one feature set such that changes to another set are negligible. We show that this problem is nearly equivalent to one of Rayleigh quotient maximization, and provide a closed-form solution to it based on solving a generalized eigenvalue equation. We use repeated computations of the corresponding optimal directions, which we call Rayleigh EigenDirections (REDs), to generate appropriately curved paths in latent space. We empirically evaluate our method using StyleGAN2 and BigGAN on the following image domains: faces, living rooms and ImageNet. We show that our method is capable of controlling various multidimensional features: face identity, geometric and semantic attributes, spatial frequency bands, pixels within a region, and the appearance and position of an object. Our work suggests that a wealth of opportunities lies in the local analysis of the geometry and semantics of latent spaces.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Notes

  1. 1.

    There is no physical ‘identity’ ground truth behind a GAN-generated portrait. However, human observers or face recognition algorithms can respond to the question “Is this the same person?” and can produce consistent judgments. Therefore ‘identity’ here denotes ‘perceptual identity’.

  2. 2.

    https://github.com/zllrunning/face-parsing.PyTorch.

References

  1. Mediapipe. https://github.com/google/mediapipe

  2. Antipov, G., Baccouche, M., Dugelay, J.L.: Face aging with conditional generative adversarial networks. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 2089–2093. IEEE (2017)

    Google Scholar 

  3. Arvanitidis, G., Hansen, L.K., Hauberg, S.: Latent space oddity: on the curvature of deep generative models. arXiv preprint arXiv:1710.11379 (2017)

  4. Balakrishnan, G., Xiong, Y., Xia, W., Perona, P.: Towards causal benchmarking of bias in face analysis algorithms. In: European Conference on Computer Vision, pp. 547–563. Springer (2020). https://doi.org/10.1007/978-3-030-74697-1_15

  5. Balestriero, R., Paris, S., Baraniuk, R.: Max-affine spline insights into deep generative networks. arXiv preprint arXiv:2002.11912 (2020)

  6. Bao, J., Chen, D., Wen, F., Li, H., Hua, G.: Towards open-set identity preserving face synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6713–6722 (2018)

    Google Scholar 

  7. Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2019)

    Google Scholar 

  8. Chen, N., Klushyn, A., Kurle, R., Jiang, X., Bayer, J., Smagt, P.: Metrics for deep generative models. In: International Conference on Artificial Intelligence and Statistics, pp. 1540–1550. PMLR (2018)

    Google Scholar 

  9. Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789–8797 (2018)

    Google Scholar 

  10. Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690–4699 (2019)

    Google Scholar 

  11. Ghojogh, B., Karray, F., Crowley, M.: Eigenvalue and generalized eigenvalue problems: Tutorial. arXiv preprint arXiv:1903.11240 (2019)

  12. Goetschalckx, L., Andonian, A., Oliva, A., Isola, P.: Ganalyze: toward visual definitions of cognitive image properties. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5744–5753 (2019)

    Google Scholar 

  13. Goodfellow, I., et al: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)

    Google Scholar 

  14. Härkönen, E., Hertzmann, A., Lehtinen, J., Paris, S.: Ganspace: discovering interpretable gan controls. In: Advances in Neural Information Processing Systems, pp. 9841–9850 (2020)

    Google Scholar 

  15. He, Z., Zuo, W., Kan, M., Shan, S., Chen, X.: Attgan: facial attribute editing by only changing what you want. IEEE Trans. Image Process. 28(11), 5464–5478 (2019)

    Article  MathSciNet  Google Scholar 

  16. Jahanian*, A., Chai*, L., Isola, P.: On the “steerability” of generative adversarial networks. In: International Conference on Learning Representations (2020)

    Google Scholar 

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

    Google Scholar 

  18. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. arXiv preprint arXiv:1912.04958 (2019)

  19. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14–16 April 2014, Conference Track Proceedings (2014)

    Google Scholar 

  20. Kocaoglu, M., Snyder, C., Dimakis, A.G., Vishwanath, S.: Causalgan: learning causal implicit generative models with adversarial training. In: International Conference on Learning Representations (2018)

    Google Scholar 

  21. Kuhnel, L., Fletcher, T., Joshi, S., Sommer, S.: Latent space non-linear statistics. arXiv preprint arXiv:1805.07632 (2018)

  22. Lample, G., Zeghidour, N., Usunier, N., Bordes, A., Denoyer, L., Ranzato, M.: Fader networks: Manipulating images by sliding attributes. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), pp. 5969–5978 (2017)

    Google Scholar 

  23. Liu, M., et al.: Stgan: a unified selective transfer network for arbitrary image attribute editing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3673–3682 (2019)

    Google Scholar 

  24. Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)

  25. Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier gans. In: International Conference on Machine Learning, pp. 2642–2651. PMLR (2017)

    Google Scholar 

  26. Or-El, R., Sengupta, S., Fried, O., Shechtman, E., Kemelmacher-Shlizerman, I.: Lifespan age transformation synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 739–755. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_44

    Chapter  Google Scholar 

  27. Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337–2346 (2019)

    Google Scholar 

  28. Plumerault, A., Borgne, H.L., Hudelot, C.: Controlling generative models with continuous factors of variations. In: International Conference on Learning Representations (2020)

    Google Scholar 

  29. Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)

  30. Shao, H., Kumar, A., Thomas Fletcher, P.: The riemannian geometry of deep generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 315–323 (2018)

    Google Scholar 

  31. Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of gans for semantic face editing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9243–9252 (2020)

    Google Scholar 

  32. Shen, Y., Luo, P., Yan, J., Wang, X., Tang, X.: Faceid-gan: Learning a symmetry three-player gan for identity-preserving face synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 821–830 (2018)

    Google Scholar 

  33. Shen, Y., Zhou, B., Luo, P., Tang, X.: Facefeat-gan: a two-stage approach for identity-preserving face synthesis. arXiv preprint arXiv:1812.01288 (2018)

  34. Shoshan, A., Bhonker, N., Kviatkovsky, I., Medioni, G.: Gan-control: Explicitly controllable gans. arXiv preprint arXiv:2101.02477 (2021)

  35. Tran, L., Yin, X., Liu, X.: Disentangled representation learning gan for pose-invariant face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1415–1424 (2017)

    Google Scholar 

  36. Tzelepis, C., Tzimiropoulos, G., Patras, I.: Warpedganspace: finding non-linear rbf paths in gan latent space. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6393–6402 (2021)

    Google Scholar 

  37. Upchurch, P., et al.: Deep feature interpolation for image content changes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7064–7073 (2017)

    Google Scholar 

  38. Voynov, A., Babenko, A.: Unsupervised discovery of interpretable directions in the gan latent space. In: International Conference on Machine Learning, pp. 9786–9796. PMLR (2020)

    Google Scholar 

  39. Wang, B., Ponce, C.R.: A geometric analysis of deep generative image models and its applications. In: International Conference on Learning Representations (2021)

    Google Scholar 

  40. 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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798–8807 (2018)

    Google Scholar 

  41. Wu, Z., Lischinski, D., Shechtman, E.: Stylespace analysis: disentangled controls for stylegan image generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12863–12872 (2021)

    Google Scholar 

  42. Xiao, T., Hong, J., Ma, J.: Elegant: Exchanging latent encodings with gan for transferring multiple face attributes. In: Proceedings of the European conference on computer vision (ECCV), pp. 168–184 (2018)

    Google Scholar 

  43. Yang, C., Shen, Y., Zhou, B.: Semantic hierarchy emerges in deep generative representations for scene synthesis. Int. J. Comput. Vis. 129(5), 1451–1466 (2021). https://doi.org/10.1007/s11263-020-01429-5

    Article  Google Scholar 

  44. Yang, H., Chai, L., Wen, Q., Zhao, S., Sun, Z., He, S.: Discovering interpretable latent space directions of gans beyond binary attributes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12177–12185 (2021)

    Google Scholar 

  45. Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Towards large-pose face frontalization in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3990–3999 (2017)

    Google Scholar 

  46. Zhu, J., et al.: Low-rank subspaces in gans. In: Advances in Neural Information Processing Systems 34 (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Guha Balakrishnan .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1825 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

Balakrishnan, G., Gadde, R., Martinez, A., Perona, P. (2022). Rayleigh EigenDirections (REDs): Nonlinear GAN Latent Space Traversals for Multidimensional Features. 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 13677. Springer, Cham. https://doi.org/10.1007/978-3-031-19790-1_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19790-1_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19789-5

  • Online ISBN: 978-3-031-19790-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics