Skip to main content

SC-wLS: Towards Interpretable Feed-forward Camera Re-localization

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13661))

Included in the following conference series:

Abstract

Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality. Feed-forward absolute camera pose regression methods directly output poses by a network, but suffer from low accuracy. Meanwhile, scene coordinate based methods are accurate, but need iterative RANSAC post-processing, which brings challenges to efficient end-to-end training and inference. In order to have the best of both worlds, we propose a feed-forward method termed SC-wLS that exploits all scene coordinate estimates for weighted least squares pose regression. This differentiable formulation exploits a weight network imposed on 2D-3D correspondences, and requires pose supervision only. Qualitative results demonstrate the interpretability of learned weights. Evaluations on 7Scenes and Cambridge datasets show significantly promoted performance when compared with former feed-forward counterparts. Moreover, our SC-wLS method enables a new capability: self-supervised test-time adaptation on the weight network. Codes and models are publicly available.

X. Wu and H. Zhao—Equal contribution.

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

References

  1. Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297–5307 (2016)

    Google Scholar 

  2. Brachmann, E., Humenberger, M., Rother, C., Sattler, T.: On the limits of pseudo ground truth in visual camera re-localisation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6218–6228 (2021)

    Google Scholar 

  3. Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6D object pose estimation using 3D object coordinates. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 536–551. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10605-2_35

    Chapter  Google Scholar 

  4. Brachmann, E., et al.: DSAC-differentiable RANSAC for camera localization. In: CVPR (2017)

    Google Scholar 

  5. Brachmann, E., Rother, C.: Learning less is more - 6D camera localization via 3D surface regression. In: CVPR (2018)

    Google Scholar 

  6. Brachmann, E., Rother, C.: Neural-guided RANSAC: learning where to sample model hypotheses. In: ICCV (2019)

    Google Scholar 

  7. Brachmann, E., Rother, C.: Visual camera re-localization from RGB and RGB-D images using DSAC. IEEE Trans. Pattern Anal. Mach. Intell. (2021)

    Google Scholar 

  8. Brahmbhatt, S., Gu, J., Kim, K., Hays, J., Kautz, J.: Geometry-aware learning of maps for camera localization. In: CVPR (2018)

    Google Scholar 

  9. Cai, M., Shen, C., Reid, I.: A hybrid probabilistic model for camera relocalization (2019)

    Google Scholar 

  10. Cao, S., Snavely, N.: Graph-based discriminative learning for location recognition. In: IJCV (2015)

    Google Scholar 

  11. Choi, S., Kim, T., Yu, W.: Performance evaluation of RANSAC family. J. Comput. Vision 24(3), 271–300 (1997)

    Article  Google Scholar 

  12. Dang, Z., Yi, K.M., Hu, Y., Wang, F., Fua, P., Salzmann, M.: Eigendecomposition-free training of deep networks for linear least-square problems. TPAMI (2020)

    Google Scholar 

  13. Ding, M., Wang, Z., Sun, J., Shi, J., Luo, P.: CamNet: coarse-to-fine retrieval for camera re-localization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2871–2880 (2019)

    Google Scholar 

  14. Gould, S., Hartley, R., Campbell, D.J.: Deep declarative networks. TPAMI (2021)

    Google Scholar 

  15. Hartley, R., Zisserman, A.: Multiple view geometry in computer vision: N-view geometry (2004)

    Google Scholar 

  16. Hays, J., Efros, A.A.: IM2GPS: estimating geographic information from a single image. In: CVPR (2008)

    Google Scholar 

  17. Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1849–1856. IEEE (2009)

    Google Scholar 

  18. Hirzer, M., Lepetit, V., Roth, P.: Smart hypothesis generation for efficient and robust room layout estimation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2912–2920 (2020)

    Google Scholar 

  19. Huang, Z., Xu, Y., Shi, J., Zhou, X., Bao, H., Zhang, G.: Prior guided dropout for robust visual localization in dynamic environments. In: ICCV (2019)

    Google Scholar 

  20. Ionescu, C., Vantzos, O., Sminchisescu, C.: Matrix backpropagation for deep networks with structured layers. In: ICCV (2015)

    Google Scholar 

  21. Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: CVPR (2017)

    Google Scholar 

  22. Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: ICCV (2015)

    Google Scholar 

  23. Lepetit, V., Fua, P., et al.: Monocular model-based 3D tracking of rigid objects: a survey. Found. Trends® Comput. Graph. Vision 1(1), 1–89 (2005)

    Google Scholar 

  24. Li, S., Xu, C., Xie, M.: A robust o (n) solution to the perspective-n-point problem. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1444–1450 (2012)

    Article  Google Scholar 

  25. Li, S., Wu, X., Cao, Y., Zha, H.: Generalizing to the open world: deep visual odometry with online adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13184–13193 (2021)

    Google Scholar 

  26. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV (2004)

    Google Scholar 

  27. Mair, E., Strobl, K.H., Suppa, M., Burschka, D.: Efficient camera-based pose estimation for real-time applications. In: 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2696–2703. IEEE (2009)

    Google Scholar 

  28. Meng, L., Tung, F., Little, J.J., Valentin, J., de Silva, C.W.: Exploiting points and lines in regression forests for RGB-D camera relocalization. In: IROS (2018)

    Google Scholar 

  29. Naseer, T., Burgard, W.: Deep regression for monocular camera-based 6-DOF global localization in outdoor environments. In: IROS (2017)

    Google Scholar 

  30. Ranftl, R., Koltun, V.: Deep fundamental matrix estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 292–309. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_18

    Chapter  Google Scholar 

  31. Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: learning feature matching with graph neural networks. In: CVPR (2020)

    Google Scholar 

  32. Sattler, T., Leibe, B., Kobbelt, L.: Efficient & effective prioritized matching for large-scale image-based localization. TPAMI (2016)

    Google Scholar 

  33. Sattler, T., Zhou, Q., Pollefeys, M., Leal-Taixe, L.: Understanding the limitations of CNN-based absolute camera pose regression. In: CVPR (2019)

    Google Scholar 

  34. Schindler, G., Brown, M., Szeliski, R.: City-scale location recognition. In: CVPR (2007)

    Google Scholar 

  35. Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104–4113 (2016)

    Google Scholar 

  36. Schönemann, P.H.: A generalized solution of the orthogonal procrustes problem. Psychometrika 31(1), 1–10 (1966)

    Article  MathSciNet  Google Scholar 

  37. Shavit, Y., Ferens, R., Keller, Y.: Learning multi-scene absolute pose regression with transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2733–2742 (2021)

    Google Scholar 

  38. Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: CVPR (2013)

    Google Scholar 

  39. Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: ICCV (2003)

    Google Scholar 

  40. Valentin, J., Nießner, M., Shotton, J., Fitzgibbon, A., Izadi, S., Torr, P.H.: Exploiting uncertainty in regression forests for accurate camera relocalization. In: CVPR (2015)

    Google Scholar 

  41. Vaswani, A., et al.: Attention is all you need (2017)

    Google Scholar 

  42. Walch, F., Hazirbas, C., Leal-Taixe, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using LSTMs for structured feature correlation. In: ICCV (2017)

    Google Scholar 

  43. Wang, B., Chen, C., Lu, C.X., Zhao, P., Trigoni, N., Markham, A.: Atloc: attention guided camera localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10393–10401 (2020)

    Google Scholar 

  44. Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642–2651 (2019)

    Google Scholar 

  45. Wang, X., Wang, X., Wang, C., Bai, X., Wu, J., Hancock, E.R.: Discriminative features matter: multi-layer bilinear pooling for camera localization. In: BMVC (2019)

    Google Scholar 

  46. Wu, C.: Towards linear-time incremental structure from motion. In: 3DV (2013)

    Google Scholar 

  47. Wu, J., Ma, L., Hu, X.: Delving deeper into convolutional neural networks for camera relocalization. In: ICRA (2017)

    Google Scholar 

  48. Xue, F., Wang, X., Yan, Z., Wang, Q., Wang, J., Zha, H.: Local supports global: deep camera relocalization with sequence enhancement. In: ICCV (2019)

    Google Scholar 

  49. Xue, F., Wu, X., Cai, S., Wang, J.: Learning multi-view camera relocalization with graph neural networks. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11372–11381. IEEE (2020)

    Google Scholar 

  50. Yan, C., Shao, B., Zhao, H., Ning, R., Zhang, Y., Xu, F.: 3D room layout estimation from a single RGB image. IEEE Trans. Multimedia 22(11), 3014–3024 (2020)

    Article  Google Scholar 

  51. Yi, K., Trulls, E., Ono, Y., Lepetit, V., Salzmann, M., Fua, P.: Learning to find good correspondences. In: CVPR (2018)

    Google Scholar 

  52. Zhang, J., et al.: Learning two-view correspondences and geometry using order-aware network. In: ICCV (2019)

    Google Scholar 

  53. Zhang, W., Kosecka, J.: Image based localization in urban environments. In: 3DPTV (2006)

    Google Scholar 

  54. Zhao, H., Lu, M., Yao, A., Guo, Y., Chen, Y., Zhang, L.: Physics inspired optimization on semantic transfer features: an alternative method for room layout estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10–18 (2017)

    Google Scholar 

  55. Zhong, L., et al.: Seeing through the occluders: robust monocular 6-DOF object pose tracking via model-guided video object segmentation. IEEE Robot. Autom. Lett. 5(4), 5159–5166 (2020)

    Article  Google Scholar 

  56. Zhou, L., et al.: KfNet: learning temporal camera relocalization using Kalman filtering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4919–4928 (2020)

    Google Scholar 

  57. Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)

    Google Scholar 

  58. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004). https://doi.org/10.1109/TIP.2003.819861

Download references

Acknowledgement

This work was supported by the National Natural Science Foundation of China under Grant 62176010.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Xin Wu .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1612 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

Wu, X., Zhao, H., Li, S., Cao, Y., Zha, H. (2022). SC-wLS: Towards Interpretable Feed-forward Camera Re-localization. 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 13661. Springer, Cham. https://doi.org/10.1007/978-3-031-19769-7_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19769-7_34

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19768-0

  • Online ISBN: 978-3-031-19769-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics