iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://doi.org/10.1007/978-3-031-72933-1_6
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control | SpringerLink
Skip to main content
Springer Nature Link
Log in

DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15097))

Included in the following conference series:

  • 50 Accesses

Abstract

Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content, specialize to user data through few-shot fine-tuning, and condition their output on other modalities, such as semantic maps. However, are they usable as large-scale data generators, e.g., to improve tasks in the perception stack, like semantic segmentation? We investigate this question in the context of autonomous driving, and answer it with a resounding “yes”. We propose an efficient data generation pipeline termed DGInStyle. First, we examine the problem of specializing a pretrained LDM to semantically-controlled generation within a narrow domain. Second, we propose a Style Swap technique to endow the rich generative prior with the learned semantic control. Third, we design a Multi-resolution Latent Fusion technique to overcome the bias of LDMs towards dominant objects. Using DGInStyle, we generate a diverse dataset of street scenes, train a domain-agnostic semantic segmentation model on it, and evaluate the model on multiple popular autonomous driving datasets. Our approach consistently increases the performance of several domain generalization methods compared to the previous state-of-the-art methods. The source code and the generated dataset are available at dginstyle.github.io.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /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 64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
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. Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves ImageNet classification. arXiv:2304.08466 (2023)

  2. Bansal, A., et al.: Universal guidance for diffusion models. arXiv:2302.07121 (2023)

  3. Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. arXiv:2302.08113 (2023)

  4. Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv:1809.11096 (2019)

  5. Cai, S., et al.: DiffDreamer: towards consistent unsupervised single-view scene extrapolation with conditional diffusion models. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2023)

    Google Scholar 

  6. Cai, S., Obukhov, A., Dai, D., Van Gool, L.: Pix2NeRF: unsupervised conditional P-GAN for single image to neural radiance fields translation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  7. Chen, K., et al.: GeoDiffusion: Text-prompted geometric control for object detection data generation. arXiv:2306.04607 (2023)

  8. Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. arXiv:2304.03373 (2023)

  9. Choi, S., Jung, S., Yun, H., Kim, J.T., Kim, S., Choo, J.: RobustNet: improving domain generalization in urban-scene segmentation via instance selective whitening. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)

    Google Scholar 

  10. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)

    Google Scholar 

  11. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2009)

    Google Scholar 

  12. Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. arXiv:2105.05233 (2021)

  13. Ding, J., Xue, N., Xia, G.S., Schiele, B., Dai, D.: HGFormer: hierarchical grouping transformer for domain generalized semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023)

    Google Scholar 

  14. Dunlap, L., Umino, A., Zhang, H., Yang, J., Gonzalez, J.E., Darrell, T.: Diversify your vision datasets with automatic diffusion-based augmentation. arXiv:2305.16289 (2023)

  15. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning (2015)

    Google Scholar 

  16. Goel, V., et al.: PAIR-diffusion: object-level image editing with structure-and-appearance paired diffusion models. arXiv:2303.17546 (2023)

  17. Gong, R., Danelljan, M., Sun, H., Mangas, J.D., Gool, L.V.: Prompting diffusion representations for cross-domain semantic segmentation. arXiv:2307.02138 (2023)

  18. Goodfellow, I.J., et al.: Generative adversarial networks. arXiv:1406.2661 (2014)

  19. Ham, C., Hays, J., Lu, J., Singh, K.K., Zhang, Z., Hinz, T.: Modulating pretrained diffusion models for multimodal image synthesis. arXiv:2302.12764 (2023)

  20. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)

    Google Scholar 

  21. He, R., et al.: Is synthetic data from generative models ready for image recognition? arXiv:2210.07574 (2023)

  22. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems (2020)

    Google Scholar 

  23. Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv:2207.12598 (2022)

  24. Hoyer, L., Dai, D., Van Gool, L.: DAFormer: improving network architectures and training strategies for domain-adaptive semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  25. Hoyer, L., Dai, D., Van Gool, L.: HRDA: context-aware high-resolution domain-adaptive semantic segmentation. arXiv:2204.13132 (2022)

  26. Hoyer, L., Dai, D., Van Gool, L.: Domain adaptive and generalizable network architectures and training strategies for semantic image segmentation. IEEE TPAMI 46(1), 220–235 (2024)

    Article  Google Scholar 

  27. Huang, J., Guan, D., Xiao, A., Lu, S.: FSDR: frequency space domain randomization for domain generalization. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)

    Google Scholar 

  28. Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv:2302.09778 (2023)

  29. Huang, W., et al.: Style projected clustering for domain generalized semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023)

    Google Scholar 

  30. Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation (2023)

    Google Scholar 

  31. Kim, S., Kim, D.H., Kim, H.: Texture learning domain randomization for domain generalized segmentation. arXiv preprint arXiv:2303.11546 (2023)

  32. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv:1312.6114 (2022)

  33. Kondapaneni, N., Marks, M., Knott, M., Guimarães, R., Perona, P.: Text-image alignment for diffusion-based perception. arXiv:2310.00031 (2023)

  34. Li, Z., Li, Y., Zhao, P., Song, R., Li, X., Yang, J.: Is synthetic data from diffusion models ready for knowledge distillation? arXiv:2305.12954 (2023)

  35. Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Guiding text-to-image diffusion model towards grounded generation. arXiv preprint arXiv:2301.05221 (2023)

  36. Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van Gool, L.: RePaint: inpainting using denoising diffusion probabilistic models. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  37. Meng, C., Song, Y., Song, J., Wu, J., Zhu, J.Y., Ermon, S.: SDEdit: image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)

  38. Mou, C., et al.: T2I-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv:2302.08453 (2023)

  39. Neuhold, G., Ollmann, T., Rota Bulo, S., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: IEEE International Conference on Computer Vision (2017)

    Google Scholar 

  40. Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net. In: European Conference on Computer Vision (2018)

    Google Scholar 

  41. Peng, D., Hu, P., Ke, Q., Liu, J.: Diffusion-based image translation with label guidance for domain adaptive semantic segmentation. In: IEEE/CVF International Conference on Computer Vision (2023)

    Google Scholar 

  42. Peng, D., Lei, Y., Hayat, M., Guo, Y., Li, W.: Semantic-aware domain generalized segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  43. Peng, D., Lei, Y., Liu, L., Zhang, P., Liu, J.: Global and local texture randomization for synthetic-to-real semantic segmentation. IEEE Trans. Image Process. 30 (2021)

    Google Scholar 

  44. Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv:2103.00020 (2021)

  45. Rezende, D.J., Mohamed, S.: Variational inference with normalizing flows. arXiv:1505.05770 (2016)

  46. Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102–118. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_7

    Chapter  Google Scholar 

  47. Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  48. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  49. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. arXiv:1505.04597 (2015)

  50. Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. arXiv:2208.12242 (2023)

  51. Saha, S., Hoyer, L., Obukhov, A., Dai, D., Van Gool, L.: EDAPS: enhanced domain-adaptive panoptic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2023)

    Google Scholar 

  52. Sakaridis, C., Dai, D., Van Gool, L.: Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation. In: IEEE International Conference on Computer Vision (2019)

    Google Scholar 

  53. Sakaridis, C., Dai, D., Van Gool, L.: ACDC: the adverse conditions dataset with correspondences for semantic driving scene understanding. In: IEEE/CVF International Conference on Computer Vision (2021)

    Google Scholar 

  54. Sariyildiz, M.B., Alahari, K., Larlus, D., Kalantidis, Y.: Fake it till you make it: learning transferable representations from synthetic imagenet clones. arXiv:2212.08420 (2023)

  55. Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems (2022)

    Google Scholar 

  56. Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502 (2022)

  57. Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv:2011.13456 (2021)

  58. Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. arXiv:2302.07944 (2023)

  59. Wang, T., Kanakis, M., Schindler, K., Van Gool, L., Obukhov, A.: Breathing new life into 3D assets with generative repainting. In: British Machine Vision Conference (2023)

    Google Scholar 

  60. Wu, W., et al.: DatasetDM: synthesizing data with perception annotations using diffusion models. arXiv:2308.06160 (2023)

  61. Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: DiffuMask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. arXiv preprint arXiv:2303.11681 (2023)

  62. Wu, Z., et al.: Synthetic data supervised salient object detection. In: ACM International Conference on Multimedia (2022)

    Google Scholar 

  63. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  64. Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., Mello, S.D.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. arXiv:2303.04803 (2023)

  65. Xue, H., Huang, Z., Sun, Q., Song, L., Zhang, W.: Freestyle layout-to-image synthesis. arXiv:2303.14412 (2023)

  66. Yang, L., Xu, X., Kang, B., Shi, Y., Zhao, H.: FreeMask: synthetic images with dense annotations make stronger segmentation models. arXiv preprint arXiv:2310.15160 (2023)

  67. Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)

    Google Scholar 

  68. Yu, J., Wang, Y., Zhao, C., Ghanem, B., Zhang, J.: FreeDoM: training-free energy-guided conditional diffusion model. arXiv:2303.09833 (2023)

  69. Yue, X., Zhang, Y., Zhao, S., Sangiovanni-Vincentelli, A., Keutzer, K., Gong, B.: Domain randomization and pyramid consistency: simulation-to-real generalization without accessing target domain data. In: IEEE/CVF International Conference on Computer Vision (2019)

    Google Scholar 

  70. Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)

  71. Zhang, M., et al.: DiffusionEngine: diffusion model is scalable data engine for object detection. arXiv:2309.03893 (2023)

  72. Zhang, Y., et al.: DatasetGAN: efficient labeled data factory with minimal human effort. arXiv:2104.06490 (2021)

  73. Zhao, S., et al.: Uni-ControlNet: all-in-one control to text-to-image diffusion models. arXiv:2305.16322 (2023)

  74. Zhao, Y., Zhong, Z., Zhao, N., Sebe, N., Lee, G.H.: Style-hallucinated dual consistency learning for domain generalized semantic segmentation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 535–552. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19815-1_31

    Chapter  Google Scholar 

  75. Zhong, Z., Zhao, Y., Lee, G.H., Sebe, N.: Adversarial style augmentation for domain generalized urban-scene segmentation. In: Advances in Neural Information Processing Systems (2022)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. ETH Zürich, Zürich, Switzerland

    Yuru Jia, Lukas Hoyer, Shengyu Huang, Tianfu Wang, Luc Van Gool, Konrad Schindler & Anton Obukhov

  2. KU Leuven, Leuven, Belgium

    Yuru Jia & Luc Van Gool

  3. INSAIT Sofia, Sofia, Bulgaria

    Luc Van Gool

Authors
  1. Yuru Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lukas Hoyer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shengyu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tianfu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Luc Van Gool
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Konrad Schindler
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Anton Obukhov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anton Obukhov .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Hessen, Germany

    Stefan Roth

  4. Princeton University, Palo Alto, CA, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 34729 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Jia, Y. et al. (2025). DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15097. Springer, Cham. https://doi.org/10.1007/978-3-031-72933-1_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72933-1_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72932-4

  • Online ISBN: 978-3-031-72933-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation