ONNX msg_chn_wacv20 depth completion

Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20 model in ONNX. The example takes a synthetic depth map, it reduces the density (variable) of the depthmap and passes it to the depth completion map to densify the depth map.

ONNX msg_chn_wacv20 depth completion


  • OpenCV, onnx and onnxruntime. Also, unrealcv is only required if you want to generate new data using unrealcv.

UnrealCV synthethic data generation

The input images and depth are generated using the UnrealCV library (https://unrealcv.org/), you can find more information about how to generate this data in this other repository for Unreal Synthetic depth generation.


pip install -r requirements.txt

ONNX model

The original models were converted to different formats (including .onnx) by PINTO0309, download the models from his repository and save them into the models folder.

Original Pytorch model

The Pytorch pretrained model was taken from the original repository.


  • Video inference (UnrealCV synthetic data):

python videoDepthEstimation.py

Inference video Example

ONNX msg_chn_wacv20 depth completion