Cargando…
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...
Autores principales: | Zheng, Yijie, Luo, Jianxin, Chen, Weiwei, Zhang, Yanyan, Sun, Haixun, Pan, Zhisong |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
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 |
Ejemplares similares
-
G2O-Pose: Real-Time Monocular 3D Human Pose Estimation Based on General Graph Optimization
por: Sun, Haixun, et al.
Publicado: (2022) -
A 3D reconstruction based on an unsupervised domain adaptive for binocular endoscopy
por: Zhang, Guo, et al.
Publicado: (2022) -
Unsupervised super-resolution reconstruction of hyperspectral histology images for whole-slide imaging
por: Ma, Ling, et al.
Publicado: (2022) -
Unsupervised super-resolution reconstruction of hyperspectral histology images for whole-slide imaging (Errata)
por: Ma, Ling, et al.
Publicado: (2022) -
Deep Unsupervised Fusion Learning for Hyperspectral Image Super Resolution
por: Liu, Zhe, et al.
Publicado: (2021)