Breaking New Ground in Monocular Depth Estimation with Dynamic Iterative Refinement and Scale Consistency
Source abstract
Abstract
Monocular depth estimation (MDE) is a critical task in computer vision with applications in autonomous driving, robotics, and augmented reality. However, predicting depth from a single image poses significant challenges, especially in dynamic scenes where moving objects introduce scale ambiguity and inaccuracies. In this paper, we propose the Dynamic Iterative Monocular Depth Estimation (DI-MDE) framework, which integrates an iterative refinement process with a novel scale-alignment module to address these issues. Our approach combines elastic depth bins that adjust dynamically based on uncertainty estimates with a scale-alignment mechanism to ensure consistency between static and dynamic regions. Leveraging self-supervised learning, DI-MDE does not require ground truth depth labels, making it scalable and applicable to real-world environments. Experimental results on standard datasets such as SUN RGB-D and KITTI demonstrate that our method achieves state-of-the-art performance, significantly improving depth prediction accuracy in dynamic scenes. This work contributes a robust and efficient solution to the challenges of monocular depth estimation, offering advancements in both depth refinement and scale consistency.
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
Department of Computer Engineering, Gachon University, Sujeong-gu, Seongnam-si 461-701, Gyeonggi-do, Republic of Korea
Department of Computer Systems, Tashkent University of Information Technologies Named After Muhammad Al-Khwarizmi, Tashkent 100200, Uzbekistan
Department of International Scientific Journals and Rankings, Alfraganus University, Yukori Karakamish Street 2a, Tashkent 100190, Uzbekistan
Department of Artificial Intelligence, Tashkent State University of Economics, Tashkent 100066, Uzbekistan
Funding
inistry of Oceans and Fisheries
References (24)
Show source-provided references
1. Akhmedov, F., Nasimov, R., and Abdusalomov, A. (2024). Dehazing Algorithm Integration with YOLO-v10 for Ship Fire Detection. Fire, 7.10.3390/fire7090332 ↗
2. Spencer, J., Tosi, F., Poggi, M., Arora, R.S., Russell, C., Hadfield, S., Bowden, R., Zhou, G., Li, Z., and Rao, Q. (2024, January 16–22). The third monocular depth estimation challenge. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPRW63382.2024.00005 ↗
3. Efficient image classification through collaborative knowledge distillation: A novel AlexNet modification approach10.1016/j.heliyon.2024.e34376 ↗
4. Marsal, R., Chabot, F., Loesch, A., Grolleau, W., and Sahbi, H. (2024, January 4–8). MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV57701.2024.00360 ↗
5. MonoSAID: Monocular 3D Object Detection based on Scene-Level Adaptive Instance Depth Estimation10.1007/s10846-023-02027-6 ↗
6. Nguyen, H.C., Wang, T., Alvarez, J.M., and Liu, M. (2024, January 16–22). Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.00994 ↗
7. Shao, S., Pei, Z., Wu, X., Liu, Z., Chen, W., and Li, Z. (2024, January 10–15). Iebins: Iterative elastic bins for monocular depth estimation. Proceedings of the Thirty-Seventh Annual Conference on Neural Information Processing Systems, Vancouver, CA, USA.10.1007/s11263-024-02293-3 ↗
8. Yu, S., Wang, Y., Zhuge, Y., Wang, L., and Lu, H. (2024, January 20–27). DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, CA, USA.10.1609/aaai.v38i7.28506 ↗
9. 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 Annual Conference on Neural Information Processing Systems 2014, Montreal, QC, Canada.
10. Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., and Navab, N. (2016, January 25–28). Deeper depth prediction with fully convolutional residual networks. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.10.1109/3DV.2016.32 ↗
11. Leveraging contextual information for monocular depth estimation10.1109/ACCESS.2020.3016008 ↗
12. Zhou, T., Brown, M., Snavely, N., and Lowe, D.G. (2017, January 21–26). Unsupervised learning of depth and ego-motion from video. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.700 ↗
13. Godard, C., Mac Aodha, O., Firman, M., and Brostow, G.J. (November, January 27). Digging into self-supervised monocular depth estimation. Proceedings of the IEEE/CVF international Conference on Computer Vision, Seoul, Republic of Korea.
14. Resolution-sensitive self-supervised monocular absolute depth estimation10.1007/s10489-024-05414-0 ↗
15. Casser, V., Pirk, S., Mahjourian, R., and Angelova, A. (2019, January 15–20). Unsupervised monocular depth and ego-motion learning with structure and semantics. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.10.1109/CVPRW.2019.00051 ↗
16. Li, Z., Bhat, S.F., and Wonka, P. (2024, January 16–22). Patchfusion: An end-to-end tile-based framework for high-resolution monocular metric depth estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.00955 ↗
17. Teed, Z., and Deng, J. (2020, January 23–28). Raft: Recurrent All-Pairs Field Transforms for Optical Flow. Proceedings of the Computer Vision–ECCV 2020, 16th European Conference, Glasgow, UK. Proceedings, Part II 16.10.1007/978-3-030-58536-5_24 ↗
18. Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., and Zhao, H. (2024, January 16–22). Depth anything: Unleashing the power of large-scale unlabeled data. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.00987 ↗
19. Enhancing flooding depth forecasting accuracy in an urban area using a Novel Trend forecasting Method10.1007/s11269-023-03725-4 ↗
20. Avazov, K., Mirzakhalilov, S., Umirzakova, S., Abdusalomov, A., and Cho, Y.I. (2024). Dynamic Focus on Tumor Boundaries: A Lightweight U-Net for MRI Brain Tumor Segmentation. Bioengineering, 11.10.3390/bioengineering11121302 ↗
21. Yuan, W., Gu, X., Dai, Z., Zhu, S., and Tan, P. (2022, January 18–24). Neural window fully-connected crfs for monocular depth estimation. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00389 ↗
22. Bhat, S.F., Alhashim, I., and Wonka, P. (2021, January 20–25). Adabins: Depth estimation using adaptive bins. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.
23. Patni, S., Agarwal, A., and Arora, C. (2024, January 16–22). ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.02672 ↗
24. Wasserman, L. (2013). All of Statistics: A Concise Course in Statistical Inference, Springer.