Abstract
Depth completion aims to recover dense depth maps from sparse depth and RGB images. Current methods achieve high accuracy at the cost of large model size and huge computation complexity, which prevent them from wider applications. In this paper, we focus on making two key issues on depth completion – feature extraction and fusion – more efficient to achieve superior trade-off in model size and accuracy: (1) we propose efficient dual-branch encoder by exploring data characteristics of different modalities which can greatly reduce the model size and inference time; (2) we propose a dynamic gated fusion module, which is guided by input sparse depth to fuse information of both RGB and sparse depth feature more efficiently by generating dynamic fusing weights. Experiments on KITTI Depth Completion and NYU Depth v2 show that our method achieves 3.5x - 10x speedup against the state-of-art method, 9x param compressing and comparable accuracy compared with state-of-the-art methods, which shows our method achieves good trade-off between performance and speed.
This work was supported in part by the National Key R&D Program of China 2020YFB1807805, in part by the National Natural Science Foundation of China under Grants 62071067, 62001054, 61771068.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cheng, X., Wang, P., Guan, C., Yang, R.: CSPN++: learning context and resource aware convolutional spatial propagation networks for depth completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10615–10622 (2020)
Dimitrievski, M., Veelaert, P., Philips, W.: Learning morphological operators for depth completion. In: Blanc-Talon, J., Helbert, D., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2018. LNCS, vol. 11182, pp. 450–461. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01449-0_38
Ferstl, D., Reinbacher, C., Ranftl, R., Rüther, M., Bischof, H.: Image guided depth upsampling using anisotropic total generalized variation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 993–1000 (2013)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361. IEEE (2012)
Giannone, G., Chidlovskii, B.: Learning common representation from RGB and depth images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016)
Hou, J., Dai, A., Nießner, M.: Revealnet: seeing behind objects in RGB-D scans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2098–2107 (2020)
Huang, Z., Fan, J., Cheng, S., Yi, S., Wang, X., Li, H.: HMS-Net: hierarchical multi-scale sparsity-invariant network for sparse depth completion. IEEE Trans. Image Process. 29, 3429–3441 (2019)
Jaritz, M., De Charette, R., Wirbel, E., Perrotton, X., Nashashibi, F.: Sparse and dense data with cnns: depth completion and semantic segmentation. In: 2018 International Conference on 3D Vision (3DV), pp. 52–60. IEEE (2018)
Lee, B.U., Jeon, H.G., Im, S., Kweon, I.S.: Depth completion with deep geometry and context guidance. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3281–3287. IEEE (2019)
Liao, Y., Huang, L., Wang, Y., Kodagoda, S., Yu, Y., Liu, Y.: Parse geometry from a line: monocular depth estimation with partial laser observation. In: 2017 IEEE international conference on robotics and automation (ICRA), pp. 5059–5066 (2017)
Ma, F., Cavalheiro, G.V., Karaman, S.: Self-supervised sparse-to-dense: self-supervised depth completion from lidar and monocular camera. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3288–3295 (2019)
Park, J., Joo, K., Hu, Z., Liu, C.K., Kweon, I.S.: Non-local spatial propagation network for depth completion. In: ECCV (2020)
Qiu, J., et al.: Deeplidar: deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3313–3322 (2019)
Shao, W., Sheng, H., Li, C.: Segment-based depth estimation in light field using graph cut. In: Zhang, S., Wirsing, M., Zhang, Z. (eds.) KSEM 2015. LNCS (LNAI), vol. 9403, pp. 248–259. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25159-2_23
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_54
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818–2826 (2016)
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. IEEE (2017)
Xu, Y., Zhu, X., Shi, J., Zhang, G., Bao, H., Li, H.: Depth completion from sparse lidar data with depth-normal constraints. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2811–2820 (2019)
Yang, Y., Wong, A., Soatto, S.: Dense depth posterior (DDP) from single image and sparse range. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3353–3362 (2019)
Zhang, Y., Funkhouser, T.: Deep depth completion of a single RGB-D image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 175–185 (2018)
Zhao, Yu., Jin, F., Wang, M., Wang, S.: Knowledge graphs meet geometry for semi-supervised monocular depth estimation. In: Li, G., Shen, H.T., Yuan, Y., Wang, X., Liu, H., Zhao, X. (eds.) KSEM 2020. LNCS (LNAI), vol. 12274, pp. 40–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-55130-8_4
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Mu, Z., Qi, Q., Wang, J., Sun, H., Liao, J. (2021). Efficient Depth Completion Network Based on Dynamic Gated Fusion. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management. KSEM 2021. Lecture Notes in Computer Science(), vol 12817. Springer, Cham. https://doi.org/10.1007/978-3-030-82153-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-82153-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82152-4
Online ISBN: 978-3-030-82153-1
eBook Packages: Computer ScienceComputer Science (R0)