Monocular Depth Estimation Based on Dilated Convolutions and Feature Fusion
Source abstract
Abstract
Depth estimation represents a prevalent research focus within the realm of computer vision. Existing depth estimation methodologies utilizing LiDAR (Light Detection and Ranging) technology typically obtain sparse depth data and are associated with elevated hardware expenses. Multi-view image-matching techniques necessitate prior knowledge of camera intrinsic parameters and frequently encounter challenges such as depth inconsistency, loss of details, and the blurring of edges. To tackle these challenges, the present study introduces a monocular depth estimation approach based on an end-to-end convolutional neural network. Specifically, a DNET backbone has been developed, incorporating dilated convolution and feature fusion mechanisms within the network architecture. By integrating semantic information from various receptive fields and levels, the model’s capacity for feature extraction is augmented, thereby enhancing its sensitivity to nuanced depth variations within the image. Furthermore, we introduce a loss function optimization algorithm specifically designed to address class imbalance, thereby enhancing the overall predictive accuracy of the model. Training and validation conducted on the NYU Depth-v2 (New York University Depth Dataset Version 2) and KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) datasets demonstrate that our approach outperforms other algorithms in terms of various evaluation metrics.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Vision and Imaging · Image Processing Techniques and Applications · Optical measurement and interference techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Dong Nanhu Road 3888, Changchun 130033, China
Navigation College, Dalian Maritime University, Linghai Road 1, Dalian 116026, China
References (24)
Show source-provided references
1. Holography, and the Future of 3D Display
2. Deep holography
3. Liu, S., Li, Y., Li, H., Wang, B., Wu, Y., and Zhang, Z. (2023). Visual Image Dehazing Using Polarimetric Atmospheric Light Estimation. Appl. Sci., 13.10.3390/app131910909 ↗
4. Research on the New Detection Method of Suppressing the Skylight Background Based on the Shearing Interference and the Phase Modulation10.1364/OE.386752 ↗
5. Liu, S., Li, H., Zhao, J., Liu, J., Zhu, Y., and Zhang, Z. (2024). Atmospheric Light Estimation Using Polarization Degree Gradient for Image Dehazing. Sensors, 24.10.3390/s24103137 ↗
6. Godard, C., Mac, A., Firman, M., and Brostow, G. (November, January 27). Digging into Self-supervised Monocular Depth Estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2019), Seoul, Republic of Korea.10.1109/ICCV.2019.00393 ↗
7. Bhat, S., Alhashim, I., and Wonka, P. (2021, January 19–25). Adabins: Depth Estimation using Adaptive Bins. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2021), Nashville, TN, USA.
8. Eigen, D., Puhrsch, C., and Fergus, R. (2014, January 8–13). Depth Map Prediction from a Single Image Using a Multi-Scale Deep Network. Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
9. Liu, F., Shen, C., and Lin, G. (2015, January 7–12). Deep Convolutional Neural Fields for Depth Estimation from a Single Image. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), Boston, MA, USA.10.1109/CVPR.2015.7299152 ↗
10. Lafferty, J., Andrew, M., and Fernando, P. (July, January 28). Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williams College, Williamstown, MA, USA.
11. Fu, H., Gong, M., Wang, C., Batmanghelich, K., and Tao, D. (2018, January 18–23). Deep Ordinal Regression Network for Monocular Depth Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00214 ↗
12. Huynh, L., Nguyen-Ha, P., Matas, J., Rahtu, E., and Heikkilä, J. (2020, January 23–28). Guiding Monocular Depth Estimation Using Depth-attention Volume. Proceedings of the European Conference on Computer Vision (ECCV 2020), Glasgow, UK.10.1007/978-3-030-58574-7_35 ↗
13. Silberman, N., Derek, H., Pushmeet, K., and Rob, F. (2012, January 7–13). Indoor Segmentation and Support Inference from RGBD Images. Proceedings of the European Conference on Computer Vision (ECCV 2012), Firenze, Italy.10.1007/978-3-642-33715-4_54 ↗
14. Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., and Nießner, M. (2017, January 21–26). ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA.10.1109/CVPR.2017.261 ↗
15. Ji, Y., Chen, Z., Xie, E., Hong, L., Liu, X., Liu, Z., Lu, T., Li, Z., and Luo, P. (2023, January 4–6). Ddp: Diffusion Model for Dense Visual Prediction. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France.10.1109/ICCV51070.2023.01987 ↗
16. Lee, J., Han, M., Kim, D., and Kweon, I. (2019, January 15–20). From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA.
17. Huang, G., Liu, Z., and Van Der Maaten, L. (2017, January 21–26). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Cision and Cattern Recognition (CVPR 2017), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
18. He, K., Zhang, X., and Ren, S. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
19. Yu, F., and Koltun, V. (2016, January 2–4). Multi-Scale Context Aggregation by Dilated Convolutions. Proceedings of the 4th International Conference on Learning Representations (ICLR), San Juan, Puerto Rico.
20. Alberto, G., Sergio, O., Sergiu, O., Victor, V., and José, G. (2017). A Review on Deep Learning Techniques Applied to Semantic Segmentation. arXiv.
21. Yann, L., Léon, B., Yoshua, B., and Patrick, H. (1998, January 15). Gradient-based Learning Applied to Document Recognition. Proceedings of the IEEE 1998, Seattle, WA, USA.
22. Lin, T., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
23. Geiger, A., Lenz, P., Stiller, C., and Urtasun, R. (2012, January 16–21). Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012), Providence, RI, USA.10.1109/CVPR.2012.6248074 ↗
24. Make3D: Learning 3D Scene Structure from a Single Still Image10.1109/TPAMI.2008.132 ↗