Skip to main content

Stereo Depth Estimation with Echoes

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13687))

Included in the following conference series:

Abstract

Stereo depth estimation is particularly amenable to local textured regions while echoes have good depth estimations for global textureless regions, thus the two modalities complement each other. Motivated by the reciprocal relationship between both modalities, in this paper, we propose an end-to-end framework named StereoEchoes for stereo depth estimation with echoes. A Cross-modal Volume Refinement module is designed to transfer the complementary knowledge of the audio modality to the visual modality at feature level. A Relative Depth Uncertainty Estimation module is further proposed to yield pixel-wise confidence for multimodal depth fusion at output space. As there is no dataset for this new problem, we introduce two Stereo-Echo datasets named Stereo-Replica and Stereo-Matterport3D for the first time. Remarkably, we show empirically that our StereoEchoes, on Stereo-Replica and Stereo-Matterport3D, outperforms stereo depth estimation methods by \(25\%/13.8\%\) RMSE, and surpasses the state-of-the-art audio-visual depth prediction method by \(25.3\%/42.3\%\) RMSE.

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

Access this chapter

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

Notes

  1. 1.

    The depth maps from stereo images and echoes are fused using weights of 0.9:0.1.

References

  1. Alwassel, H., Mahajan, D., Korbar, B., Torresani, L., Ghanem, B., Tran, D.: Self-supervised learning by cross-modal audio-video clustering. In: NeurIPS, pp. 9758–9770 (2020)

    Google Scholar 

  2. Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: ICCV, pp. 609–617 (2017)

    Google Scholar 

  3. Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV, pp. 667–676 (2017)

    Google Scholar 

  4. Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: CVPR, pp. 5410–5418 (2018)

    Google Scholar 

  5. Chen, C., et al.: SoundSpaces: audio-visual navigation in 3D environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 17–36. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_2

    Chapter  Google Scholar 

  6. Chen, Y., Xian, Y., Koepke, A., Shan, Y., Akata, Z.: Distilling audio-visual knowledge by compositional contrastive learning. In: CVPR, pp. 7016–7025 (2021)

    Google Scholar 

  7. Cheng, X., et al.: Hierarchical neural architecture search for deep stereo matching. In: NeurIPS, pp. 22158–22169 (2020)

    Google Scholar 

  8. Christensen, J.H., Hornauer, S., Stella, X.Y.: BatVision: learning to see 3D spatial layout with two ears. In: ICRA, pp. 1581–1587 (2020)

    Google Scholar 

  9. Dwibedi, D., Misra, I., Hebert, M.: Cut, paste and learn: surprisingly easy synthesis for instance detection. In: ICCV, pp. 1301–1310 (2017)

    Google Scholar 

  10. Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML, pp. 1050–1059 (2016)

    Google Scholar 

  11. Gan, C., Huang, D., Zhao, H., Tenenbaum, J.B., Torralba, A.: Music gesture for visual sound separation. In: CVPR, pp. 10478–10487 (2020)

    Google Scholar 

  12. Gao, R., Chen, C., Al-Halah, Z., Schissler, C., Grauman, K.: VisualEchoes: spatial image representation learning through echolocation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 658–676. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_38

    Chapter  Google Scholar 

  13. Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 36–54. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_3

    Chapter  Google Scholar 

  14. Gao, R., Grauman, K.: 2.5 d visual sound. In: CVPR, pp. 324–333 (2019)

    Google Scholar 

  15. Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: ICCV, pp. 3879–3888 (2019)

    Google Scholar 

  16. Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. In: CVPR, pp. 10457–10467 (2020)

    Google Scholar 

  17. Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: CVPR, pp. 3273–3282 (2019)

    Google Scholar 

  18. Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NeurIPS (2017)

    Google Scholar 

  19. Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P.: End-to-end learning of geometry and context for deep stereo regression. In: ICCV, pp. 66–75 (2017)

    Google Scholar 

  20. Kolarik, A.J., Moore, B.C., Zahorik, P., Cirstea, S., Pardhan, S.: Auditory distance perception in humans: a review of cues, development, neuronal bases, and effects of sensory loss. Attention Percept. Psychophys. 78(2), 373–395 (2016)

    Article  Google Scholar 

  21. Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: NeurIPS (2017)

    Google Scholar 

  22. Liang, Z., et al.: Learning for disparity estimation through feature constancy. In: CVPR, pp. 2811–2820 (2018)

    Google Scholar 

  23. Morgado, P., Misra, I., Vasconcelos, N.: Robust audio-visual instance discrimination. In: CVPR, pp. 12934–12945 (2021)

    Google Scholar 

  24. Morgado, P., Nvasconcelos, N., Langlois, T., Wang, O.: Self-supervised generation of spatial audio for 360 video. In: NeurIPS (2018)

    Google Scholar 

  25. Morgado, P., Vasconcelos, N., Misra, I.: Audio-visual instance discrimination with cross-modal agreement. In: CVPR, pp. 12475–12486 (2021)

    Google Scholar 

  26. Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639–658. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_39

    Chapter  Google Scholar 

  27. Pang, J., Sun, W., Ren, J., Yang, C., Yan, Q.: Cascade residual learning: a two-stage convolutional neural network for stereo matching. In: ICCV, pp. 878–886 (2017)

    Google Scholar 

  28. Parida, K.K., Srivastava, S., Sharma, G.: Beyond image to depth: improving depth prediction using echoes. In: CVPR, pp. 8268–8277 (2021)

    Google Scholar 

  29. Poggi, M., Mattoccia, S.: Learning from scratch a confidence measure. In: BMVC, vol. 2, p. 4 (2016)

    Google Scholar 

  30. Poggi, M., Pallotti, D., Tosi, F., Mattoccia, S.: Guided stereo matching. In: CVPR, pp. 979–988 (2019)

    Google Scholar 

  31. Poggi, M., Tonioni, A., Tosi, F., Mattoccia, S., Di Stefano, L.: Continual adaptation for deep stereo. IEEE Trans. Pattern Anal. Mach. Intell. (2021)

    Google Scholar 

  32. Qiu, J., et al.: DeepLidar: deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image. In: CVPR, pp. 3313–3322 (2019)

    Google Scholar 

  33. Savva, M., et al.: Habitat: a platform for embodied AI research. In: ICCV, pp. 9339–9347 (2019)

    Google Scholar 

  34. Schwarz, L.A.: Non-rigid registration using free-form deformations. Technische Universität München 6 (2007)

    Google Scholar 

  35. Shaked, A., Wolf, L.: Improved stereo matching with constant highway networks and reflective confidence learning. In: CVPR, pp. 4641–4650 (2017)

    Google Scholar 

  36. Song, X., Zhao, X., Fang, L., Hu, H., Yu, Y.: EdgeStereo: an effective multi-task learning network for stereo matching and edge detection. Int. J. Comput. Vision 128(4), 910–930 (2020)

    Article  Google Scholar 

  37. Srivastava, S., Jurie, F., Sharma, G.: Learning 2D to 3D lifting for object detection in 3D for autonomous vehicles. In: IROS, pp. 4504–4511 (2019)

    Google Scholar 

  38. Straub, J., et al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)

  39. Tosi, F., Poggi, M., Benincasa, A., Mattoccia, S.: Beyond local reasoning for stereo confidence estimation with deep learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 323–338. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_20

    Chapter  Google Scholar 

  40. Tsiami, A., Koutras, P., Maragos, P.: Stavis: spatio-temporal audiovisual saliency network. In: CVPR, pp. 4766–4776 (2020)

    Google Scholar 

  41. Vasudevan, A.B., Dai, D., Van Gool, L.: Semantic object prediction and spatial sound super-resolution with binaural sounds. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 638–655. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_37

    Chapter  Google Scholar 

  42. Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  43. Veach, E., Guibas, L.: Bidirectional estimators for light transport. In: Photorealistic Rendering Techniques, pp. 145–167 (1995)

    Google Scholar 

  44. Watanabe, K., Shimojo, S.: When sound affects vision: effects of auditory grouping on visual motion perception. Psychol. Sci. 12(2), 109–116 (2001)

    Article  Google Scholar 

  45. Watson, J., Aodha, O.M., Turmukhambetov, D., Brostow, G.J., Firman, M.: Learning stereo from single images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 722–740. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_42

    Chapter  Google Scholar 

  46. Weng, X., Kitani, K.: Monocular 3D object detection with pseudo-lidar point cloud. In: ICCVW (2019)

    Google Scholar 

  47. Xiong, X., Xiong, H., Xian, K., Zhao, C., Cao, Z., Li, X.: Sparse-to-dense depth completion revisited: sampling strategy and graph construction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 682–699. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_41

    Chapter  Google Scholar 

  48. Xu, H., Zhang, J.: AANet: adaptive aggregation network for efficient stereo matching. In: CVPR, pp. 1959–1968 (2020)

    Google Scholar 

  49. Yang, G., Zhao, H., Shi, J., Deng, Z., Jia, J.: SegStereo: exploiting semantic information for disparity estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 660–676. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_39

    Chapter  Google Scholar 

  50. Yang, K., Russell, B., Salamon, J.: Telling left from right: learning spatial correspondence of sight and sound. In: CVPR, pp. 9932–9941 (2020)

    Google Scholar 

  51. You, Y., et al.: Pseudo-lidar++: accurate depth for 3D object detection in autonomous driving. In: ICLR (2019)

    Google Scholar 

  52. Zhang, F., Prisacariu, V., Yang, R., Torr, P.H.: GA-Net: guided aggregation net for end-to-end stereo matching. In: CVPR, pp. 185–194 (2019)

    Google Scholar 

  53. Zhao, C.Q., Sun, Q.Y., Zhang, C.Z., Tang, Y., Qian, F.: Monocular depth estimation based on deep learning: an overview. SCIENCE CHINA Technol. Sci. 63(9), 1612–1627 (2020). https://doi.org/10.1007/s11431-020-1582-8

    Article  Google Scholar 

  54. Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 587–604. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_35

    Chapter  Google Scholar 

Download references

Acknowledgements

This research was supported by the National Key Research and Development Program of China under Grant No. 2018AAA0100400, and the National Natural Science Foundation of China under Grants 61976208, 62076242, 62071466, and the InnoHK project.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Gaofeng Meng .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1070 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

Zhang, C. et al. (2022). Stereo Depth Estimation with Echoes. 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 13687. Springer, Cham. https://doi.org/10.1007/978-3-031-19812-0_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19812-0_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19811-3

  • Online ISBN: 978-3-031-19812-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics