Skip to main content
SpringerLink
Log in

GeoRefine: Self-supervised Online Depth Refinement for Accurate Dense Mapping

  • 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

We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online depth refinement module leveraging self-supervision, and a global mapping module via TSDF fusion. The proposed system is online by design and achieves great robustness and accuracy via: (i) a robustified hybrid SLAM that incorporates learning-based optical flow and/or depth; (ii) self-supervised losses that leverage SLAM outputs and enforce long-term geometric consistency; (iii) careful system design that avoids degenerate cases in online depth refinement. We extensively evaluate GeoRefine on multiple public datasets and reach as low as \(5\%\) absolute relative depth errors.

P. Ji and Q. Yan—Joint first authorship.

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

Access this chapter

Log in via an institution
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

References

  1. Bian, J.W., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: NeurIPS (2019)

    Google Scholar 

  2. Bloesch, M., Czarnowski, J., Clark, R., Leutenegger, S., Davison, A.J.: Codeslam-learning a compact, optimisable representation for dense visual slam. In: CVPR, pp. 2560–2568 (2018)

    Google Scholar 

  3. Burri, M., et al.: The EuRoC micro aerial vehicle datasets. Int. J. Robot. Res. 35, 1157–1163 (2016)

    Article  Google Scholar 

  4. Cadena, C., et al.: Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans. Rob. 32(6), 1309–1332 (2016)

    Article  Google Scholar 

  5. Campos, C., Elvira, R., Rodríguez, J.J.G., Montiel, J.M., Tardós, J.D.: Orb-slam3: An accurate open-source library for visual, visual-inertial and multi-map slam. arXiv preprint arXiv:2007.11898 (2020)

  6. Czarnowski, J., Laidlow, T., Clark, R., Davison, A.J.: Deepfactors: real-time probabilistic dense monocular slam. IEEE Robot. Autom. Let. 5(2), 721–728 (2020)

    Article  Google Scholar 

  7. Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR, pp. 5828–5839 (2017)

    Google Scholar 

  8. Dai, A., Nießner, M., Zollhöfer, M., Izadi, S., Theobalt, C.: Bundlefusion: real-time globally consistent 3D reconstruction using on-the-fly surface reintegration. ToG 36(4), 1 (2017)

    Article  Google Scholar 

  9. Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. arXiv preprint arXiv:1406.2283 (2014)

  10. Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. TPAMI 40(3), 611–625 (2017)

    Article  Google Scholar 

  11. Engel, J., Schöps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834–849. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10605-2_54

    Chapter  Google Scholar 

  12. Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  13. Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: CVPR (2018)

    Google Scholar 

  14. 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 

  15. Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32, 1231–1237 (2013)

    Article  Google Scholar 

  16. Godard, C., Aodha, O.M., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV (2019)

    Google Scholar 

  17. Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR, pp. 270–279 (2017)

    Google Scholar 

  18. Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: unsupervised monocular depth learning from unknown cameras. In: CVPR (2019)

    Google Scholar 

  19. Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)

    MATH  Google Scholar 

  20. Hermann, M., Ruf, B., Weinmann, M., Hinz, S.: Self-supervised learning for monocular depth estimation from aerial imagery. arXiv preprint arXiv:2008.07246 (2020)

  21. Ji, P., Li, R., Bhanu, B., Xu, Y.: Monoindoor: towards good practice of self-supervised monocular depth estimation for indoor environments. In: ICCV, pp. 12787–12796 (2021)

    Google Scholar 

  22. Kingma, D.P., Ba, J.L.: Adam: a method for stochastic gradient descent. In: ICLR, pp. 1–15 (2015)

    Google Scholar 

  23. Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: ISMAR (2007)

    Google Scholar 

  24. Koestler, L., Yang, N., Zeller, N., Cremers, D.: Tandem: tracking and dense mapping in real-time using deep multi-view stereo. In: CoLR, pp. 34–45 (2022)

    Google Scholar 

  25. Kopf, J., Rong, X., Huang, J.B.: Robust consistent video depth estimation. In: CVPR, pp. 1611–1621 (2021)

    Google Scholar 

  26. Kümmerle, R., Grisetti, G., Strasdat, H., Konolige, K., Burgard, W.: g 2 o: A general framework for graph optimization. In: ICRA (2011)

    Google Scholar 

  27. Li, Q., et al.: Deep learning based monocular depth prediction: datasets, methods and applications. arXiv preprint arXiv:2011.04123 (2020)

  28. Li, S., Wu, X., Cao, Y., Zha, H.: Generalizing to the open world: deep visual odometry with online adaptation. In: CVPR, pp. 13184–13193 (2021)

    Google Scholar 

  29. Li, Z., et al.: Learning the depths of moving people by watching frozen people. In: CVPR, pp. 4521–4530 (2019)

    Google Scholar 

  30. Li, Z., Snavely, N.: Megadepth: learning single-view depth prediction from internet photos. In: CVPR, pp. 2041–2050 (2018)

    Google Scholar 

  31. Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. TPAMI 38(10), 2024–2039 (2015)

    Article  Google Scholar 

  32. Liu, J., et al.: Planemvs: 3d plane reconstruction from multi-view stereo. In: CVPR (2022)

    Google Scholar 

  33. Luo, X., Huang, J.B., Szeliski, R., Matzen, K., Kopf, J.: Consistent video depth estimation. TOG 39(4), 71–1 (2020)

    Article  Google Scholar 

  34. Matsuki, H., Scona, R., Czarnowski, J., Davison, A.J.: Codemapping: real-time dense mapping for sparse slam using compact scene representations. IEEE Robot. Autom. Lett. 6(4), 7105–7112 (2021)

    Article  Google Scholar 

  35. Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147–1163 (2015)

    Article  Google Scholar 

  36. Mur-Artal, R., Tardós, J.D.: ORB-SLAM2: an open-source slam system for monocular, stereo, and RGB-D cameras. IEEE Trans. Rob. 33(5), 1255–1262 (2017)

    Article  Google Scholar 

  37. Nießner, M., Zollhöfer, M., Izadi, S., Stamminger, M.: Real-time 3D reconstruction at scale using voxel hashing. ToG 32(6), 1–11 (2013)

    Article  Google Scholar 

  38. Qi, X., Liao, R., Liu, Z., Urtasun, R., Jia, J.: Geonet: geometric neural network for joint depth and surface normal estimation. In: CVPR, pp. 283–291 (2018)

    Google Scholar 

  39. Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12179–12188 (2021)

    Google Scholar 

  40. Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. arXiv preprint arXiv:1907.01341 (2019)

  41. Ranjan, A., et al.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: CVPR, pp. 12240–12249 (2019)

    Google Scholar 

  42. Ruhkamp, P., Gao, D., Chen, H., Navab, N., Busam, B.: Attention meets geometry: geometry guided spatial-temporal attention for consistent self-supervised monocular depth estimation. In: 3DV, pp. 837–847 (2021)

    Google Scholar 

  43. Schönberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR, pp. 4104–4113 (2016)

    Google Scholar 

  44. Schubert, D., Demmel, N., Usenko, V., Stückler, J., Cremers, D.: Direct sparse odometry with rolling shutter. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 699–714. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_42

    Chapter  Google Scholar 

  45. Shu, C., Yu, K., Duan, Z., Yang, K.: Feature-metric loss for self-supervised learning of depth and egomotion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 572–588. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58529-7_34

    Chapter  Google Scholar 

  46. Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33715-4_54

    Chapter  Google Scholar 

  47. Song, S., Chandraker, M., Guest, C.C.: Parallel, real-time monocular visual odometry. In: ICRA (2013)

    Google Scholar 

  48. Stanford Artificial Intelligence Laboratory et al.: Robotic operating system. http://www.ros.org

  49. Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D slam systems. In: IROS, pp. 573–580 (2012)

    Google Scholar 

  50. Tateno, K., Tombari, F., Laina, I., Navab, N.: CNN-SLAM: real-time dense monocular slam with learned depth prediction. In: CVPR (2017)

    Google Scholar 

  51. Teed, Z., Deng, J.: DeepV2D: video to depth with differentiable structure from motion. arXiv preprint arXiv:1812.04605 (2018)

  52. Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402–419. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_24

    Chapter  Google Scholar 

  53. Teed, Z., Deng, J.: Droid-slam: deep visual slam for monocular, stereo, and RGB-D cameras. arXiv preprint arXiv:2108.10869 (2021)

  54. Tiwari, L., Ji, P., Tran, Q.-H., Zhuang, B., Anand, S., Chandraker, M.: Pseudo RGB-D for self-improving monocular SLAM and depth prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 437–455. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_26

    Chapter  Google Scholar 

  55. Triggs, B., McLauchlan, P., Hartley, R., Fitzgibbon, A.: Bundle adjustment-a modern synthesis. Vision Algorithms: Theory and Practice, pp. 153–177 (2000)

    Google Scholar 

  56. Ummenhofer, B., et al.: DEMON: depth and motion network for learning monocular stereo. In: CVPR (2017)

    Google Scholar 

  57. Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: CVPR, pp. 2022–2030 (2018)

    Google Scholar 

  58. Wang, R., Pizer, S.M., Frahm, J.M.: Recurrent neural network for (un-) supervised learning of monocular video visual odometry and depth. In: CVPR (2019)

    Google Scholar 

  59. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600–612 (2004)

    Google Scholar 

  60. Xiong, M., Zhang, Z., Zhong, W., Ji, J., Liu, J., Xiong, H.: Self-supervised monocular depth and visual odometry learning with scale-consistent geometric constraints. In: IJCAI, pp. 963–969 (2021)

    Google Scholar 

  61. Yang, N., Stumberg, L.v., Wang, R., Cremers, D.: D3VO: deep depth, deep pose and deep uncertainty for monocular visual odometry. In: CVPR (2020)

    Google Scholar 

  62. Yang, N., Wang, R., Stückler, J., Cremers, D.: Deep virtual stereo odometry: leveraging deep depth prediction for monocular direct sparse odometry. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 835–852. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_50

    Chapter  Google Scholar 

  63. Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)

    Google Scholar 

  64. Zhang, Z., Cole, F., Tucker, R., Freeman, W.T., Dekel, T.: Consistent depth of moving objects in video. ACM TOG 40(4), 1–12 (2021)

    Google Scholar 

  65. Zhao, W., Liu, S., Shu, Y., Liu, Y.J.: Towards better generalization: joint depth-pose learning without posenet. In: CVPR, pp. 9151–9161 (2020)

    Google Scholar 

  66. Zhou, H., Ummenhofer, B., Brox, T.: DeepTAM: deep tracking and mapping. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 851–868. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_50

    Chapter  Google Scholar 

  67. Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR, pp. 1851–1858 (2017)

    Google Scholar 

  68. Zou, Y., Ji, P., Tran, Q.-H., Huang, J.-B., Chandraker, M.: Learning monocular visual odometry via self-supervised long-term modeling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 710–727. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_42

    Chapter  Google Scholar 

  69. Zou, Y., Luo, Z., Huang, J.-B.: DF-Net: unsupervised joint learning of depth and flow using cross-task consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 38–55. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_3

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. OPPO US Research Center, InnoPeak Technology, Inc., Palo Alto, USA

    Pan Ji, Qingan Yan, Yuxin Ma & Yi Xu

Authors
  1. Pan Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qingan Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuxin Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yi Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pan Ji .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 16387 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

Ji, P., Yan, Q., Ma, Y., Xu, Y. (2022). GeoRefine: Self-supervised Online Depth Refinement for Accurate Dense Mapping. 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_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19769-7_21

  • 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

Search

Navigation