Advertisement

CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss

Conference paper
  • 827 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12350)

Abstract

This paper proposes a hierarchical loss for monocular depth estimation, which measures the differences between the prediction and ground truth in hierarchical embedding spaces of depth maps. In order to find an appropriate embedding space, we design different architectures for hierarchical embedding generators (HEGs) and explore relevant tasks to train their parameters. Compared to conventional depth losses manually defined on a per-pixel basis, the proposed hierarchical loss can be learned in a data-driven manner. As verified by our experiments, the hierarchical loss even learned without additional labels can capture multi-scale context information, is more robust to local outliers, and thus delivers superior performance. To further improve depth accuracy, a cross level identity feature fusion network (CLIFFNet) is proposed, where low-level features with finer details are refined using more reliable high-level cues. Through end-to-end training, CLIFFNet can learn to select the optimal combinations of low-level and high-level features, leading to more effective cross level feature fusion. When trained using the proposed hierarchical loss, CLIFFNet sets a new state of the art on popular depth estimation benchmarks.

Keywords

Monocular depth estimation Hierarchical loss Hierarchical embedding space Feature fusion 

Notes

Acknowledgements

This work is supported by National Key R&D Program of China (2018AAA0102001), National Natural Science Foundation of China (61725202, U1903215, 61829102, 91538201, 61771088, 61751212, 61906031), Fundamental Research Funds for the Central Universities (DUT19GJ201), Dalian Innovation Leader’s Support Plan (2018RD07), China Postdoctoral Science Foundation (2019M661095), National Postdoctoral Program for Innovative Talent (BX20190055).

Supplementary material

504441_1_En_19_MOESM1_ESM.zip (7.1 mb)
Supplementary material 1 (zip 7297 KB)

References

  1. 1.
    Chakrabarti, A., Shao, J., Shakhnarovich, G.: Depth from a single image by harmonizing over complete local network predictions. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) NIPS, pp. 2658–2666 (2016)Google Scholar
  2. 2.
    Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: NIPS, pp. 730–738 (2016)Google Scholar
  3. 3.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)Google Scholar
  4. 4.
    Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)Google Scholar
  5. 5.
    Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV, pp. 2650–2658 (2015)Google Scholar
  6. 6.
    Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS, pp. 2366–2374 (2014)Google Scholar
  7. 7.
    Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: CVPR, pp. 2002–2011 (2018)Google Scholar
  8. 8.
    Godard, C., Aodha, O.M., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV, pp. 3827–3837 (2019)Google Scholar
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  10. 10.
    Hoiem, D., Efros, A.A., Hebert, M.: Geometric context from a single image. In: ICCV, pp. 654–661 (2005)Google Scholar
  11. 11.
    Jiao, J., Cao, Y., Song, Y., Lau, R.: Look deeper into depth: monocular depth estimation with semantic booster and attention-driven loss. In: ECCV, pp. 53–69 (2018)Google Scholar
  12. 12.
    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_43CrossRefGoogle Scholar
  13. 13.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  14. 14.
    Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 3DV, pp. 239–248 (2016)Google Scholar
  15. 15.
    Lee, J.H., Heo, M., Kim, K.R., Kim, C.S.: Single-image depth estimation based on Fourier domain analysis. In: CVPR, pp. 330–339 (2018)Google Scholar
  16. 16.
    Lee, J.H., Kim, C.S.: Monocular depth estimation using relative depth maps. In: CVPR, pp. 9729–9738 (2019)Google Scholar
  17. 17.
    Li, J., Klein, R., Yao, A.: A two-streamed network for estimating fine-scaled depth maps from single RGB images. In: ICCV, pp. 3372–3380 (2017)Google Scholar
  18. 18.
    Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: CVPR, pp. 2041–2050 (2018)Google Scholar
  19. 19.
    Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125 (2017)Google Scholar
  20. 20.
    Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: CVPR, pp. 1253–1260 (2010)Google Scholar
  21. 21.
    Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: CVPR, pp. 5162–5170 (2015)Google Scholar
  22. 22.
    Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: CVPR, pp. 716–723 (2014)Google Scholar
  23. 23.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)Google Scholar
  24. 24.
    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
  25. 25.
    Rad, M.S., Bozorgtabar, B., Marti, U.V., Basler, M., Ekenel, H.K., Thiran, J.P.: SROBB: targeted perceptual loss for single image super-resolution. In: ICCV, pp. 2710–2719 (2019)Google Scholar
  26. 26.
    Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. TPAMI 31(5), 824–840 (2008)CrossRefGoogle Scholar
  27. 27.
    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_54CrossRefGoogle Scholar
  28. 28.
    Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: ICCV, pp. 3119–3127 (2015)Google Scholar
  29. 29.
    Wang, L., et al.: DeepLens: shallow depth of field from a single image. ACM Trans. Graph. 37(6), 245:1–245:11 (2018)Google Scholar
  30. 30.
    Wang, L., Zhang, J., Wang, O., Lin, Z., Lu, H.: SDC-Depth: semantic divide-and-conquer network for monocular depth estimation. In: CVPR, June 2020Google Scholar
  31. 31.
    Watson, J., Firman, M., Brostow, G.J., Turmukhambetov, D.: Self-supervised monocular depth hints. In: ICCV, pp. 2162–2171 (2019)Google Scholar
  32. 32.
    Xian, K., et al.: Monocular relative depth perception with web stereo data supervision. In: CVPR, pp. 311–320 (2018)Google Scholar
  33. 33.
    Xu, D., Ouyang, W., Wang, X., Sebe, N.: PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: CVPR, pp. 675–684 (2018)Google Scholar
  34. 34.
    Xu, D., Wang, W., Tang, H., Liu, H., Sebe, N., Ricci, E.: Structured attention guided convolutional neural fields for monocular depth estimation. In: CVPR, pp. 3917–3925 (2018)Google Scholar
  35. 35.
    Zhi, S., Bloesch, M., Leutenegger, S., Davison, A.J.: SceneCode: monocular dense semantic reconstruction using learned encoded scene representations. In: CVPR, pp. 11776–11785 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Dalian University of TechnologyDalianChina
  2. 2.Adobe ResearchSan JoseUSA
  3. 3.Peng Cheng LabShenzhenChina
  4. 4.tiwaki Co., Ltd.KusatsuJapan

Personalised recommendations