张量流深制导滤波层
guided-filter-tf的Python项目详细描述
[Project][Paper][arXiv][Demo][Home]
正式实现fast端到端可训练引导
过滤
更快,更好和更轻用于图像处理和密集
预测。
纸张
快速端到端可训练引导过滤器
吴慧凯、郑帅、张君阁、黄凯琪
2018年CVPR
安装
pip install guided-filter-tf
用法
from guided_filter_tf.guided_filter import fast_guided_filter hr_y = fast_guided_filter(lr_x, lr_y, hr_x, r, eps, nhwc)
from guided_filter_tf.guided_filter import guided_filter hr_y = guided_filter(hr_x, init_hr_y, r, eps, nhwc)
引文
@inproceedings{wu2017fast, title = {Fast End-to-End Trainable Guided Filter}, author = {Wu, Huikai and Zheng, Shuai and Zhang, Junge and Huang, Kaiqi}, booktitle = {CVPR}, year = {2018} }