These are
MiDaS models converted to ONNX to do Monocular Depth Estimation with Unity Sentis.
Import the package into Unity using
GitHub,
OpenUPM or the
Asset Store
Example source code to run this model can be found in the
Documentation
The MiDaS models below were converted to ONNX using
this colab notebook
Input normalization is baked into the models, so the model input 'input_image' is expected to be in the [0,1] range.
Input sizes are static (e.g. 256, 384 or 512 denoted by the model suffix)
Unity Sentis is the inference engine that runs in Unity 3D. More information can be found
here