Abstract
Standard frame-based cameras have shortcomings of low dynamic range and motion blur in real applications. On the other hand, event cameras, which are bio-inspired sensors, asynchronously output the polarity values of pixel-level log intensity changes and report continuous stream data even under fast motion with a high dynamic range. Therefore, event cameras are effective in stereo depth estimation under challenging illumination conditions and/or fast motion. To estimate the disparity map with events, existing state-of-the-art event-based stereo models use the image together with past events that occurred up to the current image acquisition time. However, not all events equally contribute to the disparity estimation of the current frame since past events occur at different times under different movements with different disparity values. Therefore, events need to be carefully selected for accurate event-guided disparity estimation. In this paper, we aim to effectively deal with events that continuously occur with different disparity values in the scene depending on the camera’s movement. To this end, we first propose the differentiable event selection network to select the most relevant events for current depth estimation. Furthermore, we effectively use feature-like events triggered around the boundary of objects, leading them to serve as ideal guides in disparity estimation. To this end, we propose a neighbor cross similarity feature (NCSF) that considers the similarity between different modalities. Finally, our experiments on various datasets demonstrate the superiority of our method to estimate the depth using images and event data together. Our project code is available at: https://github.com/Chohoonhee/SCSNet.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abernethy, J., Lee, C., Tewari, A.: Perturbation techniques in online learning and optimization. Perturbations, Optimization, and Statistics, p. 223 (2016)
Ahmed, S.H., Jang, H.W., Uddin, S.N., Jung, Y.J.: Deep event stereo leveraged by event-to-image translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 882–890 (2021)
Berthet, Q., Blondel, M., Teboul, O., Cuturi, M., Vert, J.P., Bach, F.: Learning with differentiable pertubed optimizers. Adv. Neural. Inf. Process. Syst. 33, 9508–9519 (2020)
Brandli, C., Berner, R., Yang, M., Liu, S.C., Delbruck, T.: A 240 \(\times \) 180 130 db 3 \(\upmu \)s latency global shutter spatiotemporal vision sensor. IEEE J. Solid-State Cir. 49, 2333–2341 (2014)
Camunas-Mesa, L.A., Serrano-Gotarredona, T., Ieng, S.H., Benosman, R.B., Linares-Barranco, B.: On the use of orientation filters for 3D reconstruction in event-driven stereo vision. Front. Neurosci. 8, 48 (2014)
Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5410–5418 (2018)
Cheng, X., et al.: Hierarchical neural architecture search for deep stereo matching. arXiv abs/2010.13501 (2020)
Cho, H., Jeong, J., Yoon, K.J.: EOMVS: event-based omnidirectional multi-view stereo. IEEE Robot. Autom. Lett. 6(4), 6709–6716 (2021). https://doi.org/10.1109/LRA.2021.3096161
Choi, J., et al.: Learning to super resolve intensity images from events. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2768–2776 (2020)
Gehrig, M., Aarents, W., Gehrig, D., Scaramuzza, D.: DSEC: a stereo event camera dataset for driving scenarios. IEEE Robot. Autom. Lett. 6(3), 4947–4954 (2021)
Gumbel, E.J.: Statistical theory of extreme values and some practical applications: a series of lectures, vol. 33. US Government Printing Office (1954)
Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3268–3277 (2019)
Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P.: End-to-end learning of geometry and context for deep stereo regression. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 66–75 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kogler, J., Humenberger, M., Sulzbachner, C.: Event-based stereo matching approaches for frameless address event stereo data. In: International Symposium on Visual Computing, pp. 674–685. Springer (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (2012)
Laga, H., Jospin, L.V., Boussaïd, F., Bennamoun: a survey on deep learning techniques for stereo-based depth estimation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)
Liang, Z., et al.: Learning for disparity estimation through feature constancy. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2811–2820 (2018)
Lichtsteiner, P., Posch, C., Delbrück, T.: A 128 \(\times \) 128 120 db 15 \(\upmu \)s latency asynchronous temporal contrast vision sensor. IEEE J. Solid-State Circ. 43, 566–576 (2008)
Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040–4048 (2016)
Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061–3070 (2015)
Mostafavi, M., Yoon, K.J., Choi, J.: Event-intensity stereo: estimating depth by the best of both worlds. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4258–4267 (2021)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32 (2019)
Piatkowska, E., Belbachir, A., Gelautz, M.: Asynchronous stereo vision for event-driven dynamic stereo sensor using an adaptive cooperative approach. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 45–50 (2013)
Piatkowska, E., Kogler, J., Belbachir, N., Gelautz, M.: Improved cooperative stereo matching for dynamic vision sensors with ground truth evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 53–60 (2017)
Rebecq, H., Gallego, G., Mueggler, E., Scaramuzza, D.: EMVS: event-based multi-view stereo-3D reconstruction with an event camera in real-time. Int. J. Comput. Vision 126, 1394–1414 (2017)
Rogister, P., Benosman, R., Ieng, S.H., Lichtsteiner, P., Delbruck, T.: Asynchronous event-based binocular stereo matching. IEEE Trans. Neural Netw. Learn. Syst. 23(2), 347–353 (2011)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision 47, 7–42 (2004)
Tulyakov, S., Fleuret, F., Kiefel, M., Gehler, P., Hirsch, M.: Learning an event sequence embedding for dense event-based deep stereo. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1527–1537 (2019)
Tulyakov, S., Ivanov, A., Fleuret, F.: Practical deep stereo (pds): toward applications-friendly deep stereo matching. arXiv preprint arXiv:1806.01677 (2018)
Wang, L., et al.: Event-based high dynamic range image and very high frame rate video generation using conditional generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10081–10090 (2019)
Xu, H., Zhang, J.: AANet: adaptive aggregation network for efficient stereo matching. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1956–1965 (2020)
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
Zhang, F., Prisacariu, V.A., Yang, R., Torr, P.H.S.: GA-Net: guided aggregation net for end-to-end stereo matching. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 185–194 (2019)
Zhang, F., Qi, X., Yang, R., Prisacariu, V., Wah, B., Torr, P.: Domain-invariant stereo matching networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 420–439. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_25
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–595 (2018)
Zhong, Y., Dai, Y., Li, H.: Self-supervised learning for stereo matching with self-improving ability. arXiv preprint arXiv:1709.00930 (2017)
Zhu, A.Z., Chen, Y., Daniilidis, K.: Realtime time synchronized event-based stereo. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 438–452. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_27
Zhu, A.Z., Thakur, D., Özaslan, T., Pfrommer, B., Kumar, V., Daniilidis, K.: The multivehicle stereo event camera dataset: an event camera dataset for 3D perception. IEEE Robot. Autom. Lett. 3(3), 2032–2039 (2018)
Zhu, A.Z., Yuan, L., Chaney, K., Daniilidis, K.: Unsupervised event-based learning of optical flow, depth, and egomotion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 989–997 (2019)
Zou, D., et al.: Context-aware event-driven stereo matching. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 1076–1080. IEEE (2016)
Zou, D., et al.: Robust dense depth map estimation from sparse DVS stereos. In: British British Machine Vision Conference (BMVC), vol. 1 (2017)
Acknowledgements
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government (MSIT) (NRF-2022R1A2B5B03002636).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cho, H., Yoon, KJ. (2022). Selection and Cross Similarity for Event-Image Deep Stereo. 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 13692. Springer, Cham. https://doi.org/10.1007/978-3-031-19824-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-19824-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19823-6
Online ISBN: 978-3-031-19824-3
eBook Packages: Computer ScienceComputer Science (R0)