Skip to main content

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13698))

Included in the following conference series:

Abstract

Online stereo adaptation tackles the domain shift problem, caused by different environments between synthetic (training) and real (test) datasets, to promptly adapt stereo models in dynamic real-world applications such as autonomous driving. However, previous methods often fail to counteract particular regions related to dynamic objects with more severe environmental changes. To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation. In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient for the robust initialization of the baseline model. This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner. We conduct extensive experiments to verify the effectiveness of our method under three adaptation settings such as short-, mid-, and long-term sequences. Experimental results show that the proper initialization of the base stereo model by the auxiliary network enables our learning paradigm to achieve state-of-the-art performance at inference.

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (NRF-2021R1A2C2006703) and the Yonsei University Research Fund of 2021 (2021-22-0001).

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

Notes

  1. 1.

    The results with DispNetC are shown in supplementary materials.

  2. 2.

    We conducted a custom experiment using a publicly available code for each paper.

  3. 3.

    For Raft-stereo [21], a real-time version was employed which shows a much faster inference speed.

References

  1. Achtelik, M., Bachrach, A., He, R., Prentice, S., Roy, N.: Stereo vision and laser odometry for autonomous helicopters in GPS-denied indoor environments. In: SPIE Defense, Security, and Sensing, pp. 733219–733219 (2009)

    Google Scholar 

  2. Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: CVPR (2018)

    Google Scholar 

  3. Chen, Y., Van Gool, L., Schmid, C., Sminchisescu, C.: Consistency guided scene flow estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 125–141. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_8

    Chapter  Google Scholar 

  4. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: PMLR (2017)

    Google Scholar 

  5. Finn, C., Rajeswaran, A., Kakade, S., Levine, S.: Online meta-learning. In: ICML (2019)

    Google Scholar 

  6. Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740–756. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_45

    Chapter  Google Scholar 

  7. Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the Kitti dataset. Int. J. Rob. Res. 32(11), 1231–1237 (2013)

    Article  Google Scholar 

  8. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the Kitti vision benchmark suite. In: CVPR (2012)

    Google Scholar 

  9. Geiger, A., Roser, M., Urtasun, R.: Efficient large-scale stereo matching. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6492, pp. 25–38. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19315-6_3

    Chapter  Google Scholar 

  10. Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)

    Google Scholar 

  11. Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 328–341 (2008)

    Article  Google Scholar 

  12. Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNS in the wild: pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649 (2016)

  13. Hu, X., Mordohai, P.: A quantitative evaluation of confidence measures for stereo vision. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2121–2133 (2012)

    Article  Google Scholar 

  14. Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., Bry, A.: End-to-end learning of geometry and context for deep stereo regression. In: ICCV (2017)

    Google Scholar 

  15. Khamis, S., et al.: StereoNet: guided hierarchical refinement for real-time edge-aware depth prediction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 596–613. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_35

    Chapter  Google Scholar 

  16. Kim, S., Kim, S., Min, D., Sohn, K.: LAF-Net: locally adaptive fusion networks for stereo confidence estimation. In: CVPR (2019)

    Google Scholar 

  17. Kim, S., Min, D., Kim, S., Sohn, K.: Unified confidence estimation networks for robust stereo matching. IEEE Trans. Image Process. 28(3), 1299–1313 (2018)

    Article  MathSciNet  Google Scholar 

  18. Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: CVPR (2020)

    Google Scholar 

  19. Knowles, M., Peretroukhin, V., Greene, W.N., Roy, N.: Toward robust and efficient online adaptation for deep stereo depth estimation. In: ICRA (2021)

    Google Scholar 

  20. Li, D., Hospedales, T.: Online meta-learning for multi-source and semi-supervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 382–403. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_23

    Chapter  Google Scholar 

  21. Lipson, L., Teed, Z., Deng, J.: Raft-stereo: multilevel recurrent field transforms for stereo matching. In: 3DV (2021)

    Google Scholar 

  22. Liu, M.Y., Tuzel, O.: Coupled generative adversarial networks. In: NIPS (2016)

    Google Scholar 

  23. Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR (2016)

    Google Scholar 

  24. Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: CVPR (2015)

    Google Scholar 

  25. Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)

    Article  Google Scholar 

  26. Pang, J., et al.: Zoom and learn: generalizing deep stereo matching to novel domains. In: CVPR (2018)

    Google Scholar 

  27. Patricia, N., Carlucci, F.M., Caputo, B.: Deep depth domain adaptation: a case study. In: ICCV (2017)

    Google Scholar 

  28. Poggi, M., et al.: On the confidence of stereo matching in a deep-learning era: a quantitative evaluation. IEEE Trans. Pattern Anal. Mach. Intell. (2021)

    Google Scholar 

  29. Poggi, M., Tonioni, A., Tosi, F., Mattoccia, S., Di Stefano, L.: Continual adaptation for deep stereo. IEEE Trans. Pattern Anal. Mach. Intell. 1 (2021)

    Google Scholar 

  30. Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The Synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: CVPR (2016)

    Google Scholar 

  31. Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)

  32. Shen, Z., Dai, Y., Rao, Z.: CFNet: cascade and fused cost volume for robust stereo matching. In: CVPR (2021)

    Google Scholar 

  33. Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)

    Google Scholar 

  34. Tankovich, V., Hane, C., Zhang, Y., Kowdle, A., Fanello, S., Bouaziz, S.: Hitnet: Hierarchical iterative tile refinement network for real-time stereo matching. In: CVPR (2021)

    Google Scholar 

  35. Tonioni, A., Poggi, M., Mattoccia, S., Di Stefano, L.: Unsupervised adaptation for deep stereo. In: ICCV (2017)

    Google Scholar 

  36. Tonioni, A., Rahnama, O., Joy, T., Stefano, L.D., Ajanthan, T., Torr, P.H.: Learning to adapt for stereo. In: CVPR (2019)

    Google Scholar 

  37. Tonioni, A., Tosi, F., Poggi, M., Mattoccia, S., Stefano, L.D.: Real-time self-adaptive deep stereo. In: CVPR (2019)

    Google Scholar 

  38. Tosi, F., Poggi, M., Mattoccia, S., Tonioni, A., di Stefano, L.: Learning confidence measures in the wild. In: BMVC (2017)

    Google Scholar 

  39. Wang, H., Wang, X., Song, J., Lei, J., Song, M.: Faster self-adaptive deep stereo. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12622, pp. 175–191. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-69525-5_11

    Chapter  Google Scholar 

  40. Yang, G., Song, X., Huang, C., Deng, Z., Shi, J., Zhou, B.: DrivingStereo: a large-scale dataset for stereo matching in autonomous driving scenarios. In: CVPR (2019)

    Google Scholar 

  41. Zbontar, J., LeCun, Y., et al.: Stereo matching by training a convolutional neural network to compare image patches. J. Mach. Learn. Res. 17(1), 2287–2318 (2016)

    MATH  Google Scholar 

  42. Zhang, F., Qi, X., Yang, R., Prisacariu, V., Wah, B., Torr, P.: Domain-invariant stereo matching networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 420–439. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_25

    Chapter  Google Scholar 

  43. Zhang, K., Lu, J., Lafruit, G.: Cross-based local stereo matching using orthogonal integral images. IEEE Trans. Circuit Syst. Video Technol. 19(7), 1073–1079 (2009)

    Article  Google Scholar 

  44. Zhang, Y., et al.: ActiveStereoNet: end-to-end self-supervised learning for active stereo systems. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 802–819. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_48

    Chapter  Google Scholar 

  45. Zhang, Z., Lathuilière, S., Pilzer, A., Sebe, N., Ricci, E., Yang, J.: Online adaptation through meta-learning for stereo depth estimation. arXiv preprint arXiv:1904.08462 (2019)

  46. Zhou, C., Zhang, H., Shen, X., Jia, J.: Unsupervised learning of stereo matching. In: ICCV (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kwanghoon Sohn .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (zip 18725 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

Kim, K., Park, J., Lee, J., Min, D., Sohn, K. (2022). PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation. 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 13698. Springer, Cham. https://doi.org/10.1007/978-3-031-19839-7_33

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19839-7_33

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19838-0

  • Online ISBN: 978-3-031-19839-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics