ONNX-PackNet-SfM
Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX
Original image:https://commons.wikimedia.org/wiki/File:HydeStreetSF.JPG
Requirements
- Check the requirements.txt file. Additionally, pafy and youtube-dl are required for youtube video inference.
Installation
pip install -r requirements.txt
pip install pafy youtube_dl>=2021.12.17
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 models were taken from the original repository.
Examples
- Image inference:
python image_depth_estimation.py
- Video inference:
python video_depth_estimation.py
- Webcam inference:
python webcam_depth_estimation.py
Inference video Example
Original video: https://www.youtube.com/watch?v=z_9GiRz12-4
References:
- PackNet-SfM model: https://github.com/TRI-ML/packnet-sfm
- PINTO0309's model zoo: https://github.com/PINTO0309/PINTO_model_zoo
- PINTO0309's model conversion tool: https://github.com/PINTO0309/openvino2tensorflow
- Original papers: https://arxiv.org/abs/1905.02693 and https://arxiv.org/abs/2008.06630
205 Dec 30, 2022
2 Oct 4, 2021
13 Dec 10, 2022
![[CVPR 2021] Monocular depth estimation using wavelets for efficiency](https://github.com/nianticlabs/wavelet-monodepth/raw/main/assets/combo_kitti.gif)
205 Jan 2, 2023
76 Jan 3, 2023
8 Dec 29, 2022
39 Nov 21, 2022
