Cargando…
What makes the unsupervised monocular depth estimation (UMDE) model training better
Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow segmentation and depth estimation. In practice, manual labeling for dense estimation tasks is very diffic...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Publishing Group UK
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9768171/ https://www.ncbi.nlm.nih.gov/pubmed/36539595 http://dx.doi.org/10.1038/s41598-022-26613-0 |