Abstract
Depth sensors enjoy increased popularity throughout many application domains, such as robotics (SLAM) and telepresence. However, independent of technology, the depth images inevitably suffer from defects such as holes (invalid areas) and noise. In recent years, deep learning-based color image inpainting algorithms have become very powerful. Therefore, with this work, we propose to adopt existing deep learning models to reconstruct missing areas in depth images, with the possibility of real-time applications in mind. After empirical tests with various models, we chose two promising ones to build upon: a U-Net architecture with partial convolution layers that conditions the output solely on valid pixels, and a GAN architecture that takes advantage of a patch-based discriminator. For comparison, we took a standard U-Net and LaMa. All models were trained on the publically available NYUV2 dataset, which we augmented with synthetically generated noise/holes.
Our quantitative and qualitative evaluations with two public and an own dataset show that LaMa most often produced the best results, however, is also significantly slower than the others and the only one not being real-time capable. The GAN and partial convolution-based models also produced reasonably good results. Which one was superior varied from case to case but, generally, the former performed better with small-sized holes and the latter with bigger ones. The standard U-Net model that we used as a baseline was the worst and most blurry.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Armanious, K., Mecky, Y., Gatidis, S., Yang, B.: Adversarial inpainting of medical image modalities. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3267–3271 (2019)
Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299–12310 (2021)
Deng, Y., Hui, S., Zhou, S., Meng, D., Wang, J.: T-former: an efficient transformer for image inpainting. In: Proceedings of the 30th ACM International Conference on Multimedia, MM 2022, pp. 6559–6568. Association for Computing Machinery (2022)
Fujii, R., Hachiuma, R., Saito, H.: RGB-D image inpainting using generative adversarial network with a late fusion approach. ArXiv: abs/2110.07413 (2020)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967–5976 (2017)
Jeon, J., Lim, H., Seo, D.U., Myung, H.: Struct-mdc: mesh-refined unsupervised depth completion leveraging structural regularities from visual slam. IEEE Robot. Autom. Lett. 7(3), 6391–6398 (2022)
Jin, W., Zun, L., Yong, L.: Double-constraint inpainting model of a single-depth image. Sensors 20(6), 1797 (2020)
Lee, S., Yi, E., Lee, J., Kim, J.: Multi-scaled and densely connected locally convolutional layers for depth completion. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8360–8367 (2022)
Li, W., Lin, Z., Kun, Z., Qi, L., Wang, Y., Jia, J.: Mat: mask-aware transformer for large hole image inpainting. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10748–10758 (2022)
Li, Z., et al.: Promising generative adversarial network based sinogram inpainting method for ultra-limited-angle computed tomography imaging. Sensors 19(18), 3941 (2019)
Li, Z., Wu, J.: Learning deep CNN denoiser priors for depth image inpainting. Appl. Sci. 9(6), 1103 (2019)
Liu, G.: Pytorch implementation of the partial convolution layer for padding and image inpainting (2018). https://github.com/NVIDIA/partialconv
Liu, G., Reda, F.A., Shih, K.J., Wang, T.C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: European Conference on Computer Vision (2018)
Makarov, I., Borisenko, G.: Depth inpainting via vision transformer. In: 2021 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), pp. 286–291 (10 2021)
Mal, F., Karaman, S.: Sparse-to-dense: depth prediction from sparse depth samples and a single image. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–8 (2018)
Ning, W., Li, J., Zhang, L., Du, B.: Musical: multi-scale image contextual attention learning for inpainting. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligent, pp. 3748–3754 (2019)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684–10695 (2022)
Ruzic, T., Pizurica, A.: Context-aware patch-based image inpainting using Markov random field modeling. IEEE Trans. Image Process. 24(1), 444–456 (2015)
Satapathy, S., Sahay, R.R.: Robust depth map inpainting using superpixels and non-local gauss-Markov random field prior. Signal Process.: Image Commun. 98, 116378 (2021)
Shao, M., Zhang, W., Zuo, W., Meng, D.: Multi-scale generative adversarial inpainting network based on cross-layer attention transfer mechanism. Knowl.-Based Syst. 196, 105778 (2020)
Shen, L., Hong, R., Zhang, H., Zhang, H., Wang, M.: Single-shot semantic image inpainting with densely connected generative networks. In: Proceedings of the 27th ACM International Conference on Multimedia, MM 2019, pp. 1861–1869 (2019)
Starck, J.L., Elad, M., Donoho, D.: Image decomposition via the combination of sparse representations and a variational approach. IEEE Trans. Image Process. 14(10), 1570–1582 (2005)
Suvorov, R., et al.: Resolution-robust large mask inpainting with Fourier convolutions. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2149–2159 (2022)
Tao, Y., Popovic, M., Wang, Y., Digumarti, S., Chebrolu, N., Fallon, M.: 3d lidar reconstruction with probabilistic depth completion for robotic navigation. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5339–5346 (2022)
Tschumperle, D., Deriche, R.: Vector-valued image regularization with PDEs: a common framework for different applications. IEEE Trans. Pattern Anal. Machine Intell. 27(4), 506–517 (2005)
Wongsa, R.: Pytorch implementation of the paper: image inpainting for irregular holes using partial convolutions. https://github.com/ryanwongsa/Image-Inpainting (2020)
Xie, C., et al.: Image inpainting with learnable bidirectional attention maps. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8857–8866 (2019)
Yan, Z., Li, X., Li, M., Zuo, W., Shan, S.: Shift-net: image inpainting via deep feature rearrangement. In: European Conference on Computer Vision (2018)
Yeh, R., Chen, C., Lim, T.Y., Schwing, A., Hasegawa-Johnson, M., Do, M.: Semantic image inpainting with deep generative models. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6882–6890 (2017)
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.: Free-form image inpainting with gated convolution. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 4470–4479 (2019)
Yu, Y., et al.: Diverse image inpainting with bidirectional and autoregressive transformers. In Proceedings of the 29th ACM International Conference on Multimedia (2021)
Zhang, X., Zhai, D., Li, T., Zhou, Y., Lin, Y.: Image inpainting based on deep learning: a review. Inf. Fusion 90, 74–94 (2022)
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 (CVPR) (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fischer, R., Roßkamp, J., Hudcovic, T., Schlegel, A., Zachmann, G. (2023). Inpainting of Depth Images Using Deep Neural Networks for Real-Time Applications. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2023. Lecture Notes in Computer Science, vol 14362. Springer, Cham. https://doi.org/10.1007/978-3-031-47966-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-47966-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47965-6
Online ISBN: 978-3-031-47966-3
eBook Packages: Computer ScienceComputer Science (R0)