Lightweight monocular depth estimation using a fusion-improved transformer
Abstract The existing deep estimation networks often overlook the issue of computational efficiency while pursuing high accuracy. This paper proposes a lightweight self-supervised network that combines convolutional neural networks (CNN) and Transformers as the feature extraction and encoding layers...
שמור ב:
| Principais autores: | , , , , , |
|---|---|
| פורמט: | Artigo |
| שפה: | Inglês |
| יצא לאור: |
Nature Portfolio
2024-09-01
|
| סדרה: | Scientific Reports |
| נושאים: | |
| גישה מקוונת: | https://doi.org/10.1038/s41598-024-72682-8 |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|