Abstract
3D reconstruction is a basic and important task in computer vision. The overall reconstruction quality evaluation of voxel based 3D reconstruc-tion method is not high currently. This paper mainly aims at the problem that the overall reconstruction quality evaluation of voxel based 3D reconstruction methods is not high. According to the good conversion relationship between shape layer and voxels, a new shape layer based 3D voxel recon-struction network is proposed to transform the prediction problem of 3D voxels into the prediction problem of 2D depth map. Experiments show that it is superior to other voxel based 3D reconstruction methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Fu, K., Pemg, J., He, Q., et al.: Single image 3D object reconstruction based on deep learning: a review. Multimedia Tools Appl. 80(1), 463–498 (2021)
Wu, Z., Song, S., Khosla, A., et al.: 3D Shapenets: a deep representation for volumetric shapes. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)
Choy, C., Danfei, X., Gwak, J., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628–644. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_38
Akhiter, I., Sheikh, Y., Khan, S., et al.: Nonrigid structure from motion in trajectory space. In: The International Conference on Neural Information Processing Systems, pp. 41–48 (2008)
Paladini, M., Del Bue, A., Xavier, J., et al.: Optimal metric projections for deformable and articulated structure-from-motion. Int. J. Comput. Vision 96(2), 252–276 (2012)
Kumar, S., Cherian, A., Dai, Y., et al.: Scalable dense non-rigid structurefrom-motion: a grassmannian perspective. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 254–263 (2018)
Tulsiani, S., Zhou, T., Efros, A.A., et al.: Multi-view supervision for single-view reconstruction via differentiable ray consistency. In: he IEEE Conference on Computer Vision and Pattern Recognition, pp. 2626–2634 (2017)
Tatarchenko, M., Dosovitskiy, A., Brox, T.: Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. In: The IEEE International Conference on Computer Vision, pp. 2088–2096 (2017)
Richter, S.R., Roth, S.: Matryoshka networks: predicting 3d geometry via nested shape layers. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 1936–1944 (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Tolstikhin, I., Houlsby, N., Kolesnikov, A., et al.: Mlp-Mixer: an All-mlp architecture for vision (2021). arXiv preprint arXiv:2105.01601
Acknowledgement
This work was supported by the Shenzhen Foundational Research Funding under grant number JCYJ20180507183527919 and the Shenzhen Science and Technology Plan under grant number JCYJ20180306171938767.
Author information
Authors and Affiliations
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
Tang, L., Shi, S., Qin, S., Huang, X., Fan, Y. (2022). 3D Voxel Reconstruction Based on Shape Layer. In: Chu, SC., Lin, J.CW., Li, J., Pan, JS. (eds) Genetic and Evolutionary Computing. ICGEC 2021. Lecture Notes in Electrical Engineering, vol 833. Springer, Singapore. https://doi.org/10.1007/978-981-16-8430-2_28
Download citation
DOI: https://doi.org/10.1007/978-981-16-8430-2_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8429-6
Online ISBN: 978-981-16-8430-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)