Abstract
In various tasks of self-supervised monocular depth estimation, the prevalent norm has been the adoption of a U-shaped network structure, utilizing the convolution module as the foundational operator, leading to notable accomplishments. However, the inherent limitation of convolution operations, characterized by a restricted receptive field, often poses challenges in explicitly capturing long-range dependencies. The Transformer, originally designed for sequence-to-sequence prediction, presents a global self-attention mechanism capable of capturing long-range dependencies but may compromise localization abilities, lacking in low-level details. This paper introduces TransIndoor, a robust alternative for self-supervised monocular depth estimation that combines the strengths of the Transformer and convolution. TransIndoor effectively extracts both global context information and local spatial details simultaneously. Furthermore, a novel local multi-scale fusion block is introduced to enhance fine-grained details by processing skipped connections within the encoder through the primary CNN stem. The comprehensive validation of TransIndoor using the NYU Depth V2 dataset and ScanNet demonstrates its capability to generate satisfactory depth maps, addressing the limitations of existing methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cheng, D., Chen, L., Lv, C., Guo, L., Kou, Q.: Light-guided and Cross-fusion U-Net for anti-illumination image super-resolution. IEEE Trans. Circuits Syst. Video Technol. 32(12), 8436–8449 (2021)
Li, B., Huang, Y., Liu, Z., Zou, D., Yu, W.: StructDepth: leveraging the structural regularities for self-supervised indoor depth estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 12643–12653.IEEE, New York (2021)
Godard, C., mac Aodha, O., Firman, M., Brostow, G.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3827–3837. IEEE, New York (2019)
Cheng, Z., Zhang, Y., Tang, C.: Swin-depth: using transformers and multi-scale fusion for monocular-based depth estimation. IEEE Sens. J. 21(23), 26912–26920 (2021)
Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: 18th IEEE/CVF International Conference on Computer Vision, Electr Network, pp. 12159–12168. IEEE, New York (2021)
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.) Computer Vision – ECCV 2012. Lecture Notes in Computer Science, vol. 7576, pp. 746–760. Springer, Berlin (2012). https://doi.org/10.1007/978-3-642-33715-4_54
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, vol. 2017-January, pp. 2432–2443. IEEE, New York (2017)
Yu, Z., Jin, L., Gao, S.: P2Net: patch-match and plane-regularization for unsupervised indoor depth estimation. http://arxiv.org/abs/2007.07696. Accessed 15 July 2020
Wei, Y., Guo, H., Lu, J., Zhou, J.: Iterative feature matching for self-supervised indoor depth estimation. IEEE Trans. Circuits Syst. Video Technol. 32(6), 3839–3852 (2022)
Acknowledgement
The work was supported in part by Jining City Key Research and Development Plan (2021JNZY013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, H., Li, Z., Geng, Y., Wang, J., Gao, J., Lv, C. (2024). TransIndoor: Transformer Based Self-supervised Indoor Depth Estimation. In: Dong, J., Zhang, L., Cheng, D. (eds) Proceedings of the 2nd International Conference on Internet of Things, Communication and Intelligent Technology. IoTCIT 2023. Lecture Notes in Electrical Engineering, vol 1197. Springer, Singapore. https://doi.org/10.1007/978-981-97-2757-5_61
Download citation
DOI: https://doi.org/10.1007/978-981-97-2757-5_61
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2756-8
Online ISBN: 978-981-97-2757-5
eBook Packages: Computer ScienceComputer Science (R0)