Abstract
Interpolation of the sparse depth map is a fundamental task for applications such as video games or autonomous vehicles. Frequently, depth maps present a lack of information due to sensor misinterpretations or occlusion. Traditional image processing methods have been used to tackle this interpolation problem. Nowadays, convolutional neural networks have been used to solve this problem with diverse approaches. On one hand, traditional methods are simple to implement, but the model is constructed by the designer. On the other hand, convolutional networks need a large database in order to train a model and are far to be implemented in a real platform such as FPGA. The question is if it is possible to state a hybrid model that considers the advantages of both points of view. Our proposal considers the infinity Laplacian (or AMLE) which is the most straightforward operator that satisfies a set of simple axioms. Embedding a reference color image with an anisotropic metric, we propose a three-stage pipeline to interpolate depth maps: color features selection, AMLE solution, and post-filtering. Inspired by convolutional networks, we constructed two convolution max pooling stages for color features selection. Taking those features, we used them as the color reference image, which defines the metric \(g_{ij}\), and then we solved the AMLE. Finally, a second convolutional stage was applied to the interpolated map. The obtained results show that the proposed convolutional stage can be replaced by a median filter. This fact increases the performance of the complete pipeline, and this pipeline outperforms contemporary methods in the KITTI dataset showing clearly the contribution of a convolutional preprocessing stage. The convolution stage enforces strong edges and smooth textures in the reference image to let the anisotropic diffusion process fill in the empty regions bounded by strong edges.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Almansa, A., Cao, F., Gousseau, Y., Rougé, B.: Interpolation of digital elevation models using AMLE and related methods. IEEE Trans. Geosci. Remote Sens. 40(2), 314–325 (2002)
Babikir, A., Sathesh, A.: Construction of accurate crack identification on concrete structure using hybrid deep learning approach. J. Innov. Image Process. 3(2), 85–99
Bai, L., Zhao, Y., Elhousni, M., Huang, X.: Depthnet: real-time lidar point cloud depth completion for autonomous vehicles. IEEE Access 8, 227825–227833 (2020)
Caselles, V., Igual, L., Sander, O.: An axiomatic approach to scalar data interpolation on surfaces. Numerische Mathematik 102(3), 383–411 (2006)
Caselles, V., Morel, J.M., Sbert, C.: An axiomatic approach to image interpolation. IEEE Trans. Image Process. 7(2), 376–386 (1998)
Dhaya, R.: Analysis of adaptive image retrieval by transition Kalman filter approach based on intensity parameter. J. Innov. Image Process. 3(01), 7–20 (2021)
Eldesokey, A., Felsberg, M., Holmquist, K., Persson, M.: Uncertainty-aware CNNS for depth completion: uncertainty from beginning to end. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)
Imran, S., Long, Y., Liu, X., Morris, D.: Depth coefficients for depth completion. In: In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12438–12447 (2019)
Lazcano, V., Calderero, F., Ballester, C.: Biased-infinity laplacian applied to depthcompletion using a balanced anisotropic metric. In: Communications, Signal Processing, and Systems: Proceedings of the 10th International Conference on Communications, Signal Processing, and Systems (Accepted) (2021)
Lazcano, V., Calderero, F., Ballester, C.: Comparing different metrics on an anisotropic depth completion model. Int. J. Hybrid Intell. Syst. (Pre-press), pp. 1–13 (2021)
Lazcano, V., Calderero, F., Ballester, C.: Depth image completion using anisotropic operators. In: Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2020), Vol. 1383 (2021)
Li, Y., Huang, J.-B., Ahuja, N., Yang, M.H.: Joint image filtering with depth convolutional networks. Trans. Pattern Anal. Mach. Intell. 41(8), 1909–1923 (2019). https://doi.org/10.1109/TPAMI.2018.2890623
Lu, K., Barnes, N., Anwar, S., Zheng, L.: From depth what can you see? Depth completion via auxiliary image reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)
Manfredi, J., Oberman, A.M., Sviridov, A.P.: Nonlinear elliptic partial differential equation and p-harmonic functions on graphs. Differ. Integr. Eqn. 28(1/2), 79–102 (2015)
Nan, Z., Zhiyu, X., Yiman, C., Shuya, C., Chengyu, Q.: Simultaneous semantic segmentation and depth completion with constraint of boundary. Sensors 20(3), 1–25 (2020)
Oberman, A.M.: A convergent difference scheme for the infinity Laplacian: construction of absolutely minimizing Lipschitz extensions. Math. Comput. 74(251), 1217–1230 (2005)
Oliver, M., Raad, L., Ballester, C., Haro, G.: Motion inpainting by an image-based geodesic amle method. In: 25th IEEE International Conference on Image Processing (ICIP), pp. 2267–2271 (2018). https://doi.org/10.1109/ICIP.2018.8451851
Palani, U., Vasanthi, D., Begam, S.: Enhancement of medical image fusion using image processing. J. Innov. Image Process. 2(4), 165–174 (2020)
Qiu, J., Cui, Z., Zhang, Y., Zhang, X., Liu, S., Zeng, B., Pollefeys, M.: Deeplidar: deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image. In: The IEEE Conference on CVPR) (June 2019)
Sathesh, A.: Light field image coding with image prediction in redundancy. J. Soft Comput. Paradigm 2(3), 160–167 (2020)
Schneider, N., Schneider, L., Pinggera, P., Franke, U., Pollefeys, M., Stiller, C.: Semantically guided depth upsampling. In: German Conference on Pattern Recognition, pp. 37–48. Springer, Berlin (2016)
Sungheetha, A., Rajesh, S.: 3d image processing using machine learning based input processing for man-machine interaction. J. Innov. Image Process. 3(1), 1–6 (2021)
Tripathi, M.: Analysis of convolutional neural network based image classification techniques. J. Innov. Image Process. 3(2) (2021)
Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNS. In: International Conference on 3D Vision (3DV) (2017)
Yao, Y., Roxas, M., Ishikawa, R., Ando, S., Shimamura, J., Oishi, T.: Discontinuous and smooth depth completion with binary anisotropic diffusion tensor. IEEE Robot. Autom. Lett. 5(4), 5128–5135 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lazcano, V., Calderero, F. (2022). Hybrid Pipeline Infinity Laplacian Plus Convolutional Stage Applied to Depth Completion. In: Smys, S., Tavares, J.M.R.S., Balas, V.E. (eds) Computational Vision and Bio-Inspired Computing. Advances in Intelligent Systems and Computing, vol 1420. Springer, Singapore. https://doi.org/10.1007/978-981-16-9573-5_8
Download citation
DOI: https://doi.org/10.1007/978-981-16-9573-5_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9572-8
Online ISBN: 978-981-16-9573-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)