Skip to main content
SpringerLink
Log in
Book cover

European Conference on Computer Vision

ECCV 2020: Computer Vision – ECCV 2020 Workshops pp 646–661Cite as

Adversarial Transfer of Pose Estimation Regression

Part of the Lecture Notes in Computer Science book series (LNIP,volume 12535)

Abstract

We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low generalization across scenes and datasets. We identify the dataset shift an important barrier to generalization and consider transfer learning as an alternative way towards a better reuse of pose estimation models. We revise domain adaptation techniques for classification and extend them to camera pose estimation, which is a multi-regression task. We develop a deep adaptation network for learning scene-invariant image representations and use adversarial learning to generate such representations for model transfer. We enrich the network with self-supervised learning and use the adaptability theory to validate the existence of scene-invariant representation of images in two given scenes. We evaluate our network on two public datasets, Cambridge Landmarks and 7Scene, demonstrate its superiority over several baselines and compare to the state of the art methods.

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   109.99
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

Learn about institutional subscriptions

Notes

  1. 1.

    We show 3-DoF pose positions only; pose orientations show the same phenomenon.

References

  1. Balntas, V., Li, S., Prisacariu, V.: Relocnet: continuous metric learning relocalisation using neural nets. In: European Conference Computer Vision (ECCV), pp. 782–799 (2018)

    Google Scholar 

  2. Borchani, H., Varando, G., Bielza, C., Larrañaga, P.: A survey on multi-output regression. Wiley Int. Rev. Data Min. Knowl. Disc. 5(5), 216–233 (2015)

    CrossRef  Google Scholar 

  3. Brachmann, E., et al.: DSAC - differentiable RANSAC for camera localization. In: Computer Vision Pattern Recognition (CVPR), pp. 2492–2500 (2017)

    Google Scholar 

  4. Brachmann, E., Rother, C.: Learning less is more - 6D camera localization via 3D surface regression. In: Computer Vision Pattern Recognition (CVPR), pp. 4654–4662 (2018)

    Google Scholar 

  5. Brahmbhatt, S., Gu, J., Kim, K., Hays, J., Kautz, J.: Geometry-aware learning of maps for camera localization. In: Computer Vision Pattern Recognition (CVPR), pp. 2616–2625 (2018)

    Google Scholar 

  6. Bui, M., Baur, C., Navab, N., Ilic, S., Albarqouni, S.: Adversarial networks for camera pose regression and refinement. In: ICCV Workshops, vol. 2019, pp. 3778–3787 (2019)

    Google Scholar 

  7. Cao, Z., Ma, L., Long, M., Wang, J.: Partial adversarial domain adaptation. In: European Conference Computer Vision (ECCV), pp. 139–155 (2018)

    Google Scholar 

  8. Cao, Z., You, K., Long, M., Wang, J., Yang, Q.: Learning to transfer examples for partial domain adaptation. In: Computer Vision Pattern Recognition (CVPR), pp. 2985–2994 (2019)

    Google Scholar 

  9. Chen, X., Monfort, M., Liu, A., Ziebart, B.D.: Robust covariate shift regression. Proc. AISTATS. 51, 1270–1279 (2016)

    Google Scholar 

  10. Chen, X., Wang, S., Long, M., Wang, J.: Transferability vs. discriminability: batch spectral penalization for adversarial domain adaptation. In: International Conference on Machine Learning (ICML), vol. 97, pp. 1081–1090 (2019)

    Google Scholar 

  11. Cortes, C., Mohri, M.: Domain adaptation in regression. In: Proceedings 22nd International Conference on Algorithmic Learning Theory (2011)

    Google Scholar 

  12. Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 59:1–59:35 (2016)

    MathSciNet  MATH  Google Scholar 

  13. Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: International Conference on Learning Representation (ICLR) (2018)

    Google Scholar 

  14. Hoffman, J., Rodner, E., Donahue, J., Darrell, T., Saenko, K.: Efficient learning of domain-invariant image representations. CoRR arXiv:1301.3224 (2013)

  15. Kendall, A., Cipolla, R.: Modelling uncertainty in deep learning for camera relocalization. In: IEEE International Conference on Robotics and Automation, ICRA, pp. 4762–4769 (2016)

    Google Scholar 

  16. Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: Computer Vision Pattern Recognition (CVPR), pp. 6555–6564 (2017)

    Google Scholar 

  17. Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: International Conference on Computer Vision (ICCV), pp. 2938–2946 (2015)

    Google Scholar 

  18. Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: Computer Vision Pattern Recognition (CVPR), pp. 1920–1929 (2019)

    Google Scholar 

  19. Laskar, Z., Melekhov, I., Kalia, S., Kannala, J.: Camera relocalization by computing pairwise relative poses using convolutional neural network. In: IEEE International Conference on Computer Vision Workshops, pp. 929–938 (2017)

    Google Scholar 

  20. Lathuilière, S., Mesejo, P., Alameda-Pineda, X., Horaud, R.: A comprehensive analysis of deep regression. CoRR 1803.08450 (2018)

    Google Scholar 

  21. Leng, C., Zhang, H., Li, B., Cai, G., Pei, Z., He, L.: Local feature descriptor for image matching: a survey. IEEE Access 7, 6424–6434 (2019)

    CrossRef  Google Scholar 

  22. Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning (ICML), pp. 97–105 (2015)

    Google Scholar 

  23. Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer joint matching for unsupervised domain adaptation. In: Computer Vision Pattern Recognition (CVPR), pp. 1410–1417 (2014)

    Google Scholar 

  24. Melekhov, I., Ylioinas, J., Kannala, J., Rahtu, E.: Relative Camera Pose Estimation Using Convolutional Neural Networks. CoRR 1702.01381 (2017)

    Google Scholar 

  25. Radwan, N., Valada, A., Burgard, W.: Vlocnet++: deep multitask learning for semantic visual localization and odometry. IEEE Rob. Autom. Lett. 3(4), 4407–4414 (2018)

    CrossRef  Google Scholar 

  26. Rublee, E., Rabaud, V., Konolige, K., Bradski, G.R.: ORB: an efficient alternative to SIFT or SURF. In: International Conference on Computer Vision (ICCV), pp. 2564–2571 (2011)

    Google Scholar 

  27. Saha, S., Varma, G., Jawahar, C.V.: Improved visual relocalization by discovering anchor points. In: British Machine Computer Vision (BMVC), p. 164 (2018)

    Google Scholar 

  28. Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: European Conference Computer Vision (ECCV), pp. 153–168 (2018)

    Google Scholar 

  29. Sattler, T., Zhou, Q., Pollefeys, M., Leal-Taixe, L.: Understanding the limitations of CNN-based absolute camera pose regression. In: Computer Vision Pattern Recognition (CVPR), pp. 3302–3312 (2019)

    Google Scholar 

  30. Shavit, Y., Ferens, R.: Introduction to Camera Pose Estimation with Deep Learning. CoRR 1907.05272 (2019)

    Google Scholar 

  31. Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.W.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: Computer Vision Pattern Recognition (CVPR), pp. 2930–2937 (2013)

    Google Scholar 

  32. Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: Computer Vision Pattern Recognition (CVPR), pp. 1521–1528 (2011)

    Google Scholar 

  33. Valada, A., Radwan, N., Burgard, W.: Deep auxiliary learning for visual localization and odometry. In: IEEE International Conference on Robotics and Automation, ICRA, pp. 6939–6946 (2018)

    Google Scholar 

  34. Walch, F., Hazirbas, C., Leal-Taixé, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using LSTMs for structured feature correlation. In: International Conference on Computer Vision (ICCV), pp. 627–637 (2017)

    Google Scholar 

  35. Wang, M., Deng, W.: Deep visual domain adaptation: a survey. Neurocomputing 312, 135–153 (2018)

    CrossRef  Google Scholar 

  36. Yang, L., Bai, Z., Tang, C., Li, H., Furukawa, Y., Tan, P.: Sanet: scene agnostic network for camera localization. In: European Conference Computer Vision (ECCV), pp. 42–51 (2019)

    Google Scholar 

  37. You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: Computer Vision Pattern Recognition (CVPR), pp. 2720–2729 (2019)

    Google Scholar 

  38. Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: International Conference on Computer Vision (ICCV), pp. 2039–2049 (2017)

    Google Scholar 

  39. Zhou, Q., Sattler, T., Pollefeys, M., Leal-Taixe, L.: To learn or not to learn: Visual localization from essential matrices. CoRR abs/1908.01293 (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Naver Labs Europe, chemin Maupertuis 6, 38240, Meylan, France

    Boris Chidlovskii & Assem Sadek

Authors
  1. Boris Chidlovskii
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Assem Sadek
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Boris Chidlovskii .

Editor information

Editors and Affiliations

  1. University of Clermont Auvergne, Clermont Ferrand, France

    Prof. Adrien Bartoli

  2. Università degli Studi di Udine, Udine, Italy

    Andrea Fusiello

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chidlovskii, B., Sadek, A. (2020). Adversarial Transfer of Pose Estimation Regression. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12535. Springer, Cham. https://doi.org/10.1007/978-3-030-66415-2_43

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-66415-2_43

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-66414-5

  • Online ISBN: 978-3-030-66415-2

  • eBook Packages: Computer ScienceComputer Science (R0)

search

Navigation