Е-Публикации
Технически университет - София

Abstract: The reconstruction of depth information from two stereoscopic images in an efficient way remains a dynamic field of research motivated by various applications, such as autonomous driving, robotics, and others. The uncertainty of the estimated depth can be valuable in practical applications and moreover, it can improve the estimated disparity in multi-task learning settings. This work proposes an enhancement of the 2D MobileStereoNet, including efficient uncertainty estimation as part of multitask learning that simultaneously addresses disparity and uncertainty. The proposed model is evaluated using a popular stereo images dataset, and comparisons with state of the art approaches illustrate its effectiveness.

References

1. M. Mehltretter, "Joint estimation of depth and its uncertainty from stereo images using Bayesian deep learning", ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 2, pp. 69-78, 2022.
2. L. Chen, W. Wang, and P. Mordohai, "Learning the distribution of errors in stereo matching for joint disparity and uncertainty estimation", in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 17235-17244, 2023.
3. T. Schmähling, T. Müller, J. Eberhardt, and S. Elser, "Simultaneous stereo matching and confidence estimation network", J. Imaging, vol. 10, no. 8, p. 198, 2024.
4. R. Malinowski, E. Sarrazin, L. Dumas, E. Dubois, and S. Destercke, "Robust confidence intervals in stereo matching using possibility theory", arXiv preprint arXiv: 2404. 06273, 2024.
5. F. Shamsafar, S. Woerz, R. Rahim and A. Zell, "Mobilestereonet: Towards lightweight deep networks for stereo matching", In Proceedings of the IEEEE/CVF winter conference on applications of computer vision, (pp. 2417-2426), 2022.
6. A. G. Howard, M. Zhu, Bo Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "MobileNets: Efficient convolutional neural networks for mobile vision applications", arXiv preprint arXiv: 1704. 04861, 2017.
7. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L. C. Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks", In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 4510-4520), 2018.
8. A. Kendall and Y. Gal, "What uncertainties do we need in bayesian deep learning for computer vision?", aAdvances in neural information processing systems, 30, 2017.
9. E. Ilg, O. Cicek, S. Galesso, A. Klein, O. Makansi, F. Hutter, and T. Brox, "Uncertainty estimates and multi-hypotheses networks for optical flow", InaProceedings of the European Conference on Computer Vision (ECCV), a(pp. 652-667), 2018.
10. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization", aarXiv preprint arXiv: 1412. 6980, 2014.
11. N. Mayer, E. Ilg, P. Hausser, P. Fischer, D. Cremers, A. Dosovitskiy, and T. Brox. "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, pages 40404048, 2016.
12. E. Ilg, T. Saikia, M. Keuper, and T. Brox. "Occlusions, motion and depth boundaries with a generic network for disparity, optical flow or scene flow estimation", In Proceedings of the European Conference on Computer Vision, pages 614-630, 2018.
13. J. Pang, W. Sun, J. SJ Ren, C. Yang, and Q. Yan. "Cascade residual learning: A two-stage convolutional neural network for stereo matching", In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 887-895, 2017.
14. T. Saikia, Y. Marrakchi, A. Zela, F. Hutter, and T. Brox. "AutoDispNet: Improving disparity estimation with automl", In Proceedings of the IEEE International Conference on Computer Vision, pages 1812-1823, 2019.
15. Z. Liang, Y. Feng, Y. Guo, H. Liu, W. Chen, L. Qiao, Li Zhou, and J. Zhang, "Learning for disparity estimation through feature constancy", In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2811-2820, 2018.

Issue

Copyright IEEE