Abstract
Since the results of CNN methods for monocular depth estimation generally suffer the problem of visual dissatisfaction, we propose Feature Fusion GAN (FF-GAN) to address this issue. First, an end-to-end network based on encoder-decoder structure is proposed as the generator of FF-GAN, which can exploit the information of different scales. The encoder of our generator fuse features in different levels with a feature fusion module. The component which can obtain the information of multi-scale receptive field is the main part of the decoder of our generator. Second, in order to match the generator, the discriminator of FF-GAN is designed to efficiently learn the information of different scales by applying pyramid structure. Experiments on public datasets demonstrate the effectiveness of our generator and discriminator. Compared with the CNN methods, the results predicted by FF-GAN are significantly improved in terms of texture loss and edge blur while ensuring accuracy, and the visual effect is better.
This work is supported by Science and Technology Application Innovation Research Project of Zhejiang Provincial Public Security Department (2019TJYYCX007) and North China University of Technology Student Science and Technology Activities Project Funding (218051360020XN114/004).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ha, H., Im, S., Park, J., et al.: High-quality depth from uncalibrated small motion clip. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5413–5421. IEEE, Piscataway (2016)
Karsch, K., Liu, C., Kang, S.B.: Depth transfer: depth extraction from videos using nonparametric sampling. In: Hassner, T., Liu, C. (eds.) Dense Image Correspondences for Computer Vision, pp. 173–205. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-23048-1_9
Godard, C., Aodha, O., Firman, M., et al.: Digging into self-supervised monocular depth estimation. In: International Conference on Computer Vision, pp. 3827–3837 (2019)
Laina, I., Rupprecht, C., Belagiannis, V., et al.: Deeper depth prediction with fully convolutional residual networks. In: Proceedings of IEEE Conference on 3D vision, pp. 239–248. IEEE, Piscataway (2016)
Zhuo, W., Salzmann, M., He, X.M., et al.: Indoor scene structure analysis for single image depth estimation. In: Conference on Computer Vision and Pattern Recognition, pp. 614–622. IEEE Press, New York (2015)
Liu, F.Y., Shen, C.H., Lin, G.S., et al.: Learning depth from single monocular images using deep convolutional neural field. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024–2039 (2016)
Yang, N., Wang, R., Stückler, J., Cremers, D.: Deep virtual stereo odometry: leveraging deep depth prediction for monocular direct sparse odometry. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 835–852. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_50
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv: 1411.1784v1. https://arxiv.org/abs/1411.1784. Accessed 20 April 2020
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
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving the KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition, pp. 3354–3361. IEEE Press, New York (2012)
Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Proceedings of International Conference on Neural Information Processing Systems, pp. 2366–2374 (2014)
Liao, B., Li, H.W.: Image depth estimation model based on atrous convolutional neural network. J. Comput. Appl. 39(1), 267–274 (2019)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. IEEE, Piscataway (2016)
Ranjan, A., Jampani, V., Balles, L., et al.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 12240–12249 (2019)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems, pp. 2672–2680 (2014)
Isola, P., Zhu, J.Y., Zhou, T.H., et al.: Image-to-image translation with conditional adversarial networks. In: Conference on Computer Vision and Pattern Recognition, pp. 5967–5976 (2017)
Zhu, J.Y., Park, T., Isola, P., et al.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: International Conference on Computer Vision, pp. 2242–2251 (2017)
Mejjati, Y.A., Richardt, C., Tompkin, J., et al.: Unsupervised attention-guided image-to-image translation. In: The 32nd Annual Conference on Neural Information Processing Systems, pp. 3693–3703 (2018)
Chen, L., Papandreou, G., Schroff, F., et al.: Rethinking atrous convolution for semantic image segmentation. arXiv Preprint: 1706.05587 (2017)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Ma, F., Karaman, S.: Sparse-to-dense: depth prediction from sparse depth samples and a single image. In: International Conference on Robotics and Automation, pp. 1–8. IEEE Press, New York (2018)
Blau, Y., Mechrez, R., Timofte, R., Michaeli, T., Zelnik-Manor, L.: The 2018 PIRM challenge on perceptual image super-resolution. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 334–355. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_21
Ma, C., Yang, C., Yang, X., et al.: Learning a no-reference quality metric for single-image super-resolution. Comput. Vis. Image Underst. 158(1), 1–16 (2017)
Mittal, A., Soundararajan, R., Bovik, A.C., et al.: Making a completely blind image quality analyzer. IEEE Sign. Process. Lett. 20(3), 209–212 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Jia, R., Li, T., Yuan, F. (2020). FF-GAN: Feature Fusion GAN for Monocular Depth Estimation. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12305. Springer, Cham. https://doi.org/10.1007/978-3-030-60633-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-60633-6_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60632-9
Online ISBN: 978-3-030-60633-6
eBook Packages: Computer ScienceComputer Science (R0)