Affiliation:
1. School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
Abstract
Monocular panoramic depth estimation has various applications in robotics and autonomous driving due to its ability to perceive the entire field of view. However, panoramic depth estimation faces two significant challenges: global context capturing and distortion awareness. In this paper, we propose a new framework for panoramic depth estimation that can simultaneously address panoramic distortion and extract global context information, thereby improving the performance of panoramic depth estimation. Specifically, we introduce an attention mechanism into the multi-scale dilated convolution and adaptively adjust the receptive field size between different spatial positions, designing the adaptive attention dilated convolution module, which effectively perceives distortion. At the same time, we design the global scene understanding module to integrate global context information into the feature maps generated using the feature extractor. Finally, we trained and evaluated our model on three benchmark datasets which contains the virtual and real-world RGB-D panorama datasets. The experimental results show that the proposed method achieves competitive performance, comparable to existing techniques in both quantitative and qualitative evaluations. Furthermore, our method has fewer parameters and more flexibility, making it a scalable solution in mobile AR.
Funder
Natural Science Foundation of Jilin Provincial Department of Science and Technology
National Natural Science Foundation
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference55 articles.
1. 3d scene geometry estimation from 360 imagery: A survey;Pinto;ACM Comput. Surv.,2022
2. Ai, H., Cao, Z., Zhu, J., Bai, H., Chen, Y., and Wang, L. (2022). Deep Learning for Omnidirectional Vision: A Survey and New Perspectives. arXiv.
3. Zioulis, N., Karakottas, A., Zarpalas, D., and Daras, P. (2018, January 8–14). Omnidepth: Dense depth estimation for indoors spherical panoramas. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.
4. Tateno, K., Navab, N., and Tombari, F. (2018, January 8–14). Distortion-aware convolutional filters for dense prediction in panoramic images. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.
5. Distortion-aware monocular depth estimation for omnidirectional images;Chen;IEEE Signal Process. Lett.,2021