Skip to main content
Springer Nature Link
Log in

Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation

  • 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

Self-supervised monocular depth estimation has received much attention recently in computer vision. Most of the existing works in literature aggregate multi-scale features for depth prediction via either straightforward concatenation or element-wise addition, however, such feature aggregation operations generally neglect the contextual consistency between multi-scale features. Addressing this problem, we propose the Self-Distilled Feature Aggregation (SDFA) module for simultaneously aggregating a pair of low-scale and high-scale features and maintaining their contextual consistency. The SDFA employs three branches to learn three feature offset maps respectively: one offset map for refining the input low-scale feature and the other two for refining the input high-scale feature under a designed self-distillation manner. Then, we propose an SDFA-based network for self-supervised monocular depth estimation, and design a self-distilled training strategy to train the proposed network with the SDFA module. Experimental results on the KITTI dataset demonstrate that the proposed method outperforms the comparative state-of-the-art methods in most cases. The code is available at https://github.com/ZM-Zhou/SDFA-Net_pytorch.

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

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Cardace, A., Ramirez, P.Z., Salti, S., Di Stefano, L.: Shallow features guide unsupervised domain adaptation for semantic segmentation at class boundaries. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1160–1170 (2022)

    Google Scholar 

  2. Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: connecting flow, depth, and camera. In: ICCV, pp. 7063–7072 (2019)

    Google Scholar 

  3. Chen, Z., et al.: Revealing the reciprocal relations between self-supervised stereo and monocular depth estimation. In: ICCV, pp. 15529–15538 (2021)

    Google Scholar 

  4. Cheng, B., Saggu, I.S., Shah, R., Bansal, G., Bharadia, D.: \(S^3\)Net: semantic-aware self-supervised depth estimation with monocular videos and synthetic data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 52–69. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58577-8_4

    Chapter  Google Scholar 

  5. Cheng, Z., Zhang, Y., Tang, C.: Swin-depth: using transformers and multi-scale fusion for monocular-based depth estimation. IEEE Sens. J. 21(23), 26912–26920 (2021)

    Article  Google Scholar 

  6. Choi, H., et al.: Adaptive confidence thresholding for monocular depth estimation. In: ICCV, pp. 12808–12818 (2021)

    Google Scholar 

  7. Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)

  8. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)

    Google Scholar 

  9. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)

    Google Scholar 

  10. Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)

    Google Scholar 

  11. Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, pp. 2366–2374 (2014)

    Google Scholar 

  12. 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 

  13. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR, pp. 3354–3361 (2012)

    Google Scholar 

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

    Google Scholar 

  15. Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV, pp. 3828–3838 (2019)

    Google Scholar 

  16. GonzalezBello, J.L., Kim, M.: Forget about the lidar: self-supervised depth estimators with med probability volumes. Adv. Neural. Inf. Process. Syst. 33, 12626–12637 (2020)

    Google Scholar 

  17. GonzalezBello, J.L., Kim, M.: PLADE-Net: towards pixel-level accuracy for self-supervised single-view depth estimation with neural positional encoding and distilled matting loss. In: CVPR, pp. 6851–6860 (2021)

    Google Scholar 

  18. GonzalezBello, J.L., Kim, M.: Self-supervised deep monocular depth estimation with ambiguity boosting. IEEE TPAMI (2021)

    Google Scholar 

  19. Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. IJCV 129(6), 1789–1819 (2021)

    Article  Google Scholar 

  20. Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3d packing for self-supervised monocular depth estimation. In: CVPR, pp. 2485–2494 (2020)

    Google Scholar 

  21. Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. In: International Conference on Learning Representations (ICLR) (2020)

    Google Scholar 

  22. Guo, X., Li, H., Yi, S., Ren, J., Wang, X.: Learning monocular depth by distilling cross-domain stereo networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 506–523. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_30

    Chapter  Google Scholar 

  23. Hirschmuller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: CVPR, vol. 2, pp. 807–814. IEEE (2005)

    Google Scholar 

  24. Huang, S., Lu, Z., Cheng, R., He, C.: FaPN: feature-aligned pyramid network for dense image prediction. In: ICCV, pp. 864–873 (2021)

    Google Scholar 

  25. Huang, Z., Wei, Y., Wang, X., Liu, W., Huang, T.S., Shi, H.: AlignSeg: feature-aligned segmentation networks. IEEE TPAMI 44(1), 550–557 (2021)

    Google Scholar 

  26. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)

    Google Scholar 

  27. 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 

  28. Jiao, Y., Tran, T.D., Shi, G.: EffiScene: efficient per-pixel rigidity inference for unsupervised joint learning of optical flow, depth, camera pose and motion segmentation. In: CVPR, pp. 5538–5547 (2021)

    Google Scholar 

  29. Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43

    Chapter  Google Scholar 

  30. Johnston, A., Carneiro, G.: Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In: CVPR, pp. 4756–4765 (2020)

    Google Scholar 

  31. Jung, H., Park, E., Yoo, S.: Fine-grained semantics-aware representation enhancement for self-supervised monocular depth estimation. In: ICCV, pp. 12642–12652 (2021)

    Google Scholar 

  32. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  33. Klingner, M., Termöhlen, J.-A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 582–600. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_35

    Chapter  Google Scholar 

  34. Li, X., et al.: Improving semantic segmentation via decoupled body and edge supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 435–452. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58520-4_26

    Chapter  Google Scholar 

  35. Li, X., et al.: Semantic flow for fast and accurate scene parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 775–793. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_45

    Chapter  Google Scholar 

  36. Liu, L., Song, X., Wang, M., Liu, Y., Zhang, L.: Self-supervised monocular depth estimation for all day images using domain separation. In: ICCV, pp. 12737–12746 (2021)

    Google Scholar 

  37. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012–10022 (2021)

    Google Scholar 

  38. Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3d geometric constraints. In: CVPR, pp. 5667–5675 (2018)

    Google Scholar 

  39. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. Adv. Neural. Inf. Process. Syst. 32, 8026–8037 (2019)

    Google Scholar 

  40. Peng, R., Wang, R., Lai, Y., Tang, L., Cai, Y.: Excavating the potential capacity of self-supervised monocular depth estimation. In: ICCV, pp. 15560–15569 (2021)

    Google Scholar 

  41. Pilzer, A., Lathuiliere, S., Sebe, N., Ricci, E.: Refine and distill: exploiting cycle-inconsistency and knowledge distillation for unsupervised monocular depth estimation. In: CVPR, pp. 9768–9777 (2019)

    Google Scholar 

  42. Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: CVPR, pp. 3227–3237 (2020)

    Google Scholar 

  43. Ramamonjisoa, M., Firman, M., Watson, J., Lepetit, V., Turmukhambetov, D.: Single image depth prediction with wavelet decomposition. In: CVPR, pp. 11089–11098 (2021)

    Google Scholar 

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

    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. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  47. Tosi, F., Aleotti, F., Poggi, M., Mattoccia, S.: Learning monocular depth estimation infusing traditional stereo knowledge. In: CVPR, pp. 9799–9809 (2019)

    Google Scholar 

  48. Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNs. In: 2017 International Conference on 3D Vision (3DV), pp. 11–20 (2017)

    Google Scholar 

  49. Wang, K., et al.: Regularizing nighttime weirdness: efficient self-supervised monocular depth estimation in the dark. In: ICCV, pp. 16055–16064 (2021)

    Google Scholar 

  50. Wang, L., Wang, Y., Wang, L., Zhan, Y., Wang, Y., Lu, H.: Can scale-consistent monocular depth be learned in a self-supervised scale-invariant manner? In: ICCV, pp. 12727–12736 (2021)

    Google Scholar 

  51. Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV, pp. 568–578 (2021)

    Google Scholar 

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

    Google Scholar 

  53. Watson, J., Firman, M., Brostow, G.J., Turmukhambetov, D.: Self-supervised monocular depth hints. In: ICCV (2019)

    Google Scholar 

  54. Yang, G., Tang, H., Ding, M., Sebe, N., Ricci, E.: Transformer-based attention networks for continuous pixel-wise prediction. In: ICCV, pp. 16269–16279 (2021)

    Google Scholar 

  55. Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR, pp. 1983–1992 (2018)

    Google Scholar 

  56. Zhou, J., Wang, Y., Qin, K., Zeng, W.: Moving indoor: unsupervised video depth learning in challenging environments. In: ICCV, pp. 8618–8627 (2019)

    Google Scholar 

  57. 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 

  58. Zhou, Z., Fan, X., Shi, P., Xin, Y.: R-MSFM: recurrent multi-scale feature modulation for monocular depth estimating. In: ICCV, pp. 12777–12786 (2021)

    Google Scholar 

  59. Zhu, S., Brazil, G., Liu, X.: The edge of depth: explicit constraints between segmentation and depth. In: CVPR, pp. 13116–13125 (2020)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant Nos. U1805264 and 61991423), the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No. XDB32050100), the Beijing Municipal Science and Technology Project (Grant No. Z211100011021004).

Author information

Authors and Affiliations

  1. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China

    Zhengming Zhou & Qiulei Dong

  2. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China

    Zhengming Zhou & Qiulei Dong

  3. Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, 100190, China

    Qiulei Dong

Authors
  1. Zhengming Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qiulei Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qiulei Dong .

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 752 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

Zhou, Z., Dong, Q. (2022). Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation. 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_41

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19769-7_41

  • 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