A Convolutional Neural Network for Nonrigid Structure from Motion
In this study, we propose a reconstruction and optimization neural network (RONN), a novel neural network for nonrigid structure from motion, which is completed by an unsupervised convolution neural network. Compared with the traditional method for directly solving 3D structures, our model focuses o...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | International Journal of Digital Multimedia Broadcasting |
| Online Access: | http://dx.doi.org/10.1155/2022/3582037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832562306077163520 |
|---|---|
| author | Yaming Wang Xiangyang Peng Wenqing Huang Meiliang Wang |
| author_facet | Yaming Wang Xiangyang Peng Wenqing Huang Meiliang Wang |
| author_sort | Yaming Wang |
| collection | DOAJ |
| description | In this study, we propose a reconstruction and optimization neural network (RONN), a novel neural network for nonrigid structure from motion, which is completed by an unsupervised convolution neural network. Compared with the traditional method for directly solving 3D structures, our model focuses on depth information that is lost owing to projection. This mathematical model is developed using a convolutional neural network with three modules for integration, reconstruction, and optimization, as well as two prior-free loss functions. The proposed RONN achieves competitive accuracy on several tested sequences and high visual quality of various real video sequences. |
| format | Article |
| id | doaj-art-14f8157afdf44ab390529337297f5871 |
| institution | Kabale University |
| issn | 1687-7586 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Digital Multimedia Broadcasting |
| spelling | doaj-art-14f8157afdf44ab390529337297f58712025-02-03T01:22:56ZengWileyInternational Journal of Digital Multimedia Broadcasting1687-75862022-01-01202210.1155/2022/3582037A Convolutional Neural Network for Nonrigid Structure from MotionYaming Wang0Xiangyang Peng1Wenqing Huang2Meiliang Wang3Pattern Recognition and Computer Vision LabPattern Recognition and Computer Vision LabPattern Recognition and Computer Vision LabZhejiang Key Laboratory of DDIMCCPIn this study, we propose a reconstruction and optimization neural network (RONN), a novel neural network for nonrigid structure from motion, which is completed by an unsupervised convolution neural network. Compared with the traditional method for directly solving 3D structures, our model focuses on depth information that is lost owing to projection. This mathematical model is developed using a convolutional neural network with three modules for integration, reconstruction, and optimization, as well as two prior-free loss functions. The proposed RONN achieves competitive accuracy on several tested sequences and high visual quality of various real video sequences.http://dx.doi.org/10.1155/2022/3582037 |
| spellingShingle | Yaming Wang Xiangyang Peng Wenqing Huang Meiliang Wang A Convolutional Neural Network for Nonrigid Structure from Motion International Journal of Digital Multimedia Broadcasting |
| title | A Convolutional Neural Network for Nonrigid Structure from Motion |
| title_full | A Convolutional Neural Network for Nonrigid Structure from Motion |
| title_fullStr | A Convolutional Neural Network for Nonrigid Structure from Motion |
| title_full_unstemmed | A Convolutional Neural Network for Nonrigid Structure from Motion |
| title_short | A Convolutional Neural Network for Nonrigid Structure from Motion |
| title_sort | convolutional neural network for nonrigid structure from motion |
| url | http://dx.doi.org/10.1155/2022/3582037 |
| work_keys_str_mv | AT yamingwang aconvolutionalneuralnetworkfornonrigidstructurefrommotion AT xiangyangpeng aconvolutionalneuralnetworkfornonrigidstructurefrommotion AT wenqinghuang aconvolutionalneuralnetworkfornonrigidstructurefrommotion AT meiliangwang aconvolutionalneuralnetworkfornonrigidstructurefrommotion AT yamingwang convolutionalneuralnetworkfornonrigidstructurefrommotion AT xiangyangpeng convolutionalneuralnetworkfornonrigidstructurefrommotion AT wenqinghuang convolutionalneuralnetworkfornonrigidstructurefrommotion AT meiliangwang convolutionalneuralnetworkfornonrigidstructurefrommotion |