Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution

1.下载项目 

git clone https://github.com/compphoto/BoostingMonocularDepth.git

2.创建环境

conda create -n HighResDepth python=3.7
conda activate HighResDepth

3 实验

Download our mergenet model weights from here 

3. 1 To use MiDas-v2 or LeReS as base

conda install pytorch torchvision opencv cudatoolkit=10.2 -c pytorch
conda install matplotlib
conda install scipy
conda install scikit-image

【相关下载】

• For MiDaS-v2, download the model weights from MiDas-v2     直接下载model.pt
• For LeReS, download the mod