Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55. Yi, L., Shao, L., Savva, M., Huang, H., Zhou, Y., Wang, Q., Graham, B., Engelcke, M., Klokov, R., Lempitsky, V., Gan, Y., Wang, P., Liu, K., Yu, F., Shui, P., Hu, B., Zhang, Y., Li, Y., Bu, R., Sun, M., Wu, W., Jeong, M., Choi, J., Kim, C., Geetchandra, A., Murthy, N., Ramu, B., Manda, B., Ramanathan, M., Kumar, G., Preetham, P., Srivastava, S., Bhugra, S., Lall, B., Haene, C., Tulsiani, S., Malik, J., Lafer, J., Jones, R., Li, S., Lu, J., Jin, S., Yu, J., Huang, Q., Kalogerakis, E., Savarese, S., Hanrahan, P., Funkhouser, T., Su, H., & Guibas, L. arXiv:1710.06104 [cs], October, 2017. arXiv: 1710.06104
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55 [link]Paper  abstract   bibtex   
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.
@article{yi_largescale_2017,
	title = {Large-{Scale} {3D} {Shape} {Reconstruction} and {Segmentation} from {ShapeNet} {Core55}},
	url = {http://arxiv.org/abs/1710.06104},
	abstract = {We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.},
	language = {en},
	urldate = {2020-10-01},
	journal = {arXiv:1710.06104 [cs]},
	author = {Yi, Li and Shao, Lin and Savva, Manolis and Huang, Haibin and Zhou, Yang and Wang, Qirui and Graham, Benjamin and Engelcke, Martin and Klokov, Roman and Lempitsky, Victor and Gan, Yuan and Wang, Pengyu and Liu, Kun and Yu, Fenggen and Shui, Panpan and Hu, Bingyang and Zhang, Yan and Li, Yangyan and Bu, Rui and Sun, Mingchao and Wu, Wei and Jeong, Minki and Choi, Jaehoon and Kim, Changick and Geetchandra, Angom and Murthy, Narasimha and Ramu, Bhargava and Manda, Bharadwaj and Ramanathan, M. and Kumar, Gautam and Preetham, P. and Srivastava, Siddharth and Bhugra, Swati and Lall, Brejesh and Haene, Christian and Tulsiani, Shubham and Malik, Jitendra and Lafer, Jared and Jones, Ramsey and Li, Siyuan and Lu, Jie and Jin, Shi and Yu, Jingyi and Huang, Qixing and Kalogerakis, Evangelos and Savarese, Silvio and Hanrahan, Pat and Funkhouser, Thomas and Su, Hao and Guibas, Leonidas},
	month = oct,
	year = {2017},
	note = {arXiv: 1710.06104},
	keywords = {wolai, 导师推荐},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021