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.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 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.
References
Mediapipe. https://github.com/google/mediapipe
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)
Arvanitidis, G., Hansen, L.K., Hauberg, S.: Latent space oddity: on the curvature of deep generative models. arXiv preprint arXiv:1710.11379 (2017)
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
Balestriero, R., Paris, S., Baraniuk, R.: Max-affine spline insights into deep generative networks. arXiv preprint arXiv:2002.11912 (2020)
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)
Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2019)
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)
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)
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)
Ghojogh, B., Karray, F., Crowley, M.: Eigenvalue and generalized eigenvalue problems: Tutorial. arXiv preprint arXiv:1903.11240 (2019)
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)
Goodfellow, I., et al: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Härkönen, E., Hertzmann, A., Lehtinen, J., Paris, S.: Ganspace: discovering interpretable gan controls. In: Advances in Neural Information Processing Systems, pp. 9841–9850 (2020)
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)
Jahanian*, A., Chai*, L., Isola, P.: On the “steerability” of generative adversarial networks. In: International Conference on Learning Representations (2020)
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)
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)
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)
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)
Kuhnel, L., Fletcher, T., Joshi, S., Sommer, S.: Latent space non-linear statistics. arXiv preprint arXiv:1805.07632 (2018)
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)
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)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier gans. In: International Conference on Machine Learning, pp. 2642–2651. PMLR (2017)
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
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)
Plumerault, A., Borgne, H.L., Hudelot, C.: Controlling generative models with continuous factors of variations. In: International Conference on Learning Representations (2020)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
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)
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)
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)
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)
Shoshan, A., Bhonker, N., Kviatkovsky, I., Medioni, G.: Gan-control: Explicitly controllable gans. arXiv preprint arXiv:2101.02477 (2021)
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)
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)
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)
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)
Wang, B., Ponce, C.R.: A geometric analysis of deep generative image models and its applications. In: International Conference on Learning Representations (2021)
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)
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)
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)
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
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)
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)
Zhu, J., et al.: Low-rank subspaces in gans. In: Advances in Neural Information Processing Systems 34 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)