To begin with, clone the RoboDepth repository to the desired location:
cd models/ # desired location
git clone https://github.com/ldkong1205/RoboDepth.git
Our benchmark currently supports the following depth estimation algorithms:
-
Supervised Depth Estimation
-
Self-Supervised Depth Estimation
-
Semi-Supervised Depth Estimation
To evaluate the robustness of MonoDepth2 under common corruptions, run the following:
cd zoo/MonoDepth2
sh evaluate_kittic.sh
# --load_weights_folder: "path to the pretrained weights"
# --eval_mono or --eval_stereo: "set eval mode for mono and stereo"
To evaluate the robustness of DIFFNet under common corruptions, run the following:
cd zoo/DIFFNet
sh evaluate_kittic.sh
# --load_weights_folder: "path to the pretrained weights"
# --eval_mono or --eval_stereo: "set eval mode for mono and stereo"