midas

MiDaS

Input

(Image from kitti dataset http://www.cvlibs.net/datasets/kitti/raw_data.php)

Shape : (1, 3, 128, 384)

Output

Shape : (1, 128, 384)

usage

Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.

For the sample image,

$ python3 midas.py

If you want to specify the input image, put the image path after the --input option.
You can use --savepath option to change the name of the output file to save.

$ python3 midas.py --input IMAGE_PATH --savepath SAVE_IMAGE_PATH

By adding the --video option, you can input the video.
If you pass 0 as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.

$ python3 midas.py --video VIDEO_PATH

Reference

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

Framework

Pytorch

Model Format

ONNX opset=11

Netron

midas.onnx.prototxt