Unsupervised 3D Reconstruction with Multi-Measure and High-Resolution Loss

Multi-view 3D reconstruction technology based on deep learning is developing rapidly. Unsupervised learning has become a research hotspot because it does not need ground truth labels. The current unsupervised method mainly uses 3DCNN to regularize the cost volume to regression image depth. This appr...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Yijie, Luo, Jianxin, Chen, Weiwei, Zhang, Yanyan, Sun, Haixun, Pan, Zhisong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9824241/
https://www.ncbi.nlm.nih.gov/pubmed/36616737
http://dx.doi.org/10.3390/s23010136

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9824241/
https://www.ncbi.nlm.nih.gov/pubmed/36616737
http://dx.doi.org/10.3390/s23010136

Ejemplares similares