Abstract
3D room layout reconstruction from a single RGB panoramic image has been an emerging research topic in recent years. To achieve better prediction accuracy, in this paper, we propose a new approach to predict 3D room layout from a single panoramic image. Our reconstruction flow follows a common framework which is same as LayoutNet [9] and HorizonNet [4]; however, we redesign a new deep learning architecture with recurrent neural networks (RNNs) encoder–decoder as an extension for keypoints refinement and use a gradient ascent optimization algorithm to minimize the similar loss. Experiments on both cuboid-shaped and general Manhattan layouts show that the proposed work outperforms recent algorithms in prediction accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Fernandez-Labrador, C., Facil, J.M., Perez-Yus, A., Demonceaux, C., Guerrero, J.: Corners for layout: end-to-end layout recovery from 360 images. IEEE Robot. Autom. Lett. 5(2), 1255–1262 (2020)
Gioi, R., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a fast line segment detector with a false detection control (2008)
Lee, C.Y., Badrinarayanan, V., Malisiewicz, T., Rabinovich, A.: Roomnet: end-to-end room layout estimation. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Sun, C., Hsiao, C.W., Sun, M., Chen, H.T.: Horizonnet: learning room layout with 1d representation and pano stretch data augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1047–1056 (2019)
Yang, S.T., Wang, F.E., Peng, C.H., Wonka, P., Sun, M., Chu, H.K.: Dula-net: a dual-projection network for estimating room layouts from a single RGB panorama. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3363–3372 (2019)
Zhang, Y., Song, S., **, T., **ao, J.: Panocontext: a whole-room 3D context model for panoramic scene understanding. In: European Conference on Computer Vision (2014)
Zhang, Y., Song, S., Tan, P., **ao, J.: Panocontext: a whole-room 3D context model for panoramic scene understanding. In: European Conference on Computer Vision, pp. 668–686. Springer (2014)
Zou, C., Su, J.W., Peng, C.H., Colburn, A., Shan, Q., Wonka, P., Chu, H.K., Hoiem, D.: 3D Manhattan room layout reconstruction from a single 360 image (2019)
Zou, C., Colburn, A., Shan, Q., Hoiem, D.: Layoutnet: reconstructing the 3D room layout from a single RGB image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2051–2059 (2018)
Acknowledgements
Wei Li is supported by SCUT XK2060021005.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhao, S., Li, W. (2022). ResRnnNet: Learning to Reconstruct the 3D Room Layout from a Single RGB Panorama. In: Chu, SC., Chen, SH., Meng, Z., Ryu, K.H., Tsihrintzis, G.A. (eds) Advances in Intelligent Information Hiding and Multimedia Signal Processing. Smart Innovation, Systems and Technologies, vol 277. Springer, Singapore. https://doi.org/10.1007/978-981-19-1057-9_31
Download citation
DOI: https://doi.org/10.1007/978-981-19-1057-9_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1056-2
Online ISBN: 978-981-19-1057-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)