DIFFNet

This repo is for Self-Supervised Monocular DepthEstimation with Internal Feature Fusion(arXiv), BMVC2021

A new backbone for self-supervised depth estimaiton.

If you think it is not a bad work, please consider citing it.

@article{diffnet_bmvc,
    title = {Self-Supervised Monocular DepthEstimation with Internal Feature Fusion},
    author  = { Hang Zhou, David Greenwood and Sarah Taylor},
    booktitle = {The British Machine Vision Conference (BMVC)},
    month = {November},
    year = {2021}}

** Paper, implementation details and trained models are coming soon **

Comparing with others

Evaluation on selected hard cases:

Trained weights

• diffnet_640x192
• diffnet_640x192_ms
• diffnet_1024x320

Acknowledgement

Thanks the authors for their works:

• monodepth2
• HRNet