stevenlol / stereonet Goto Github PK

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018

If you want to communicate with me about the StereoNet, please concact me without hesitating. My email:

[email protected]

my model result

Now, my model's speed can achieve 60-25FPS on 540*960 img with the best result of 1.87 EPE_all with 16X multi model， 1.95 EPE_all with 16X single model 1.32 EPE_all with 8X single model 1.48EPE_all with 8X multi model on sceneflow dataset by end-to-end training. the following are the side outputs and the prediction example

train example

test example(outputs of 16single model and GT)

Citation

• refercence[1]

If you find our work useful in your research, please consider citing:

@inproceedings{khamis2018stereonet, title={Stereonet: Guided hierarchical refinement for real-time edge-aware depth prediction}, author={Khamis, Sameh and Fanello, Sean and Rhemann, Christoph and Kowdle, Adarsh and Valentin, Julien and Izadi, Shahram}, booktitle={Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany}, pages={8--14}, year={2018} }

Introduction

I implement the real-time stereo model according to the StereoNet model in pytorch. The speed can reach 30FPS with top performance. The speed can reach 60FPS with lower performance.

License

• Our code is released under MIT License (see LICENSE file for details).

Installaton

• python3.6
• pytorch0.4

Usage

• run main8Xmulti.py

Updates

• finetune the performance beating the original paper.

To do

• optimize the inference speed

pretrain model

• coming soon.

Thanks

• Thanks to Sameh Khamis' help