EC-DSRNet

Joint Discontinuity-Aware Depth Map Super-Resolution via Dual-Tasks Driven Unfolding Network

Lijun Zhao*, Jialong Zhang, Jinjing Zhang, Huihui Bai, Anhong Wang

The Architecture of EC-DSENet

Results:

Dependencies

• python3.7+
• pytorch1.9+
• torchvision

Datasets

We follow Ye et al. and use the same datasets. Please refer to here to download the preprocessed datasets and extract them into ./data/ folder.

Train

python train.py

Test

Please execute python test.py on the terminal to save images. For evaluate images, please execute python evaluate.py.

Ackownledgements

This code is built based on PMBANet. We thank the authors for sharing the codes.

Citation

If you find our work useful for your research, please cite us:

@article{zhao2024EC-DSRNet,
  title={Joint Discontinuity-Aware Depth Map Super-Resolution via Dual-Tasks Driven Unfolding Network},
  author={Lijun Zhao*, Jialong Zhang, Jinjing Zhang, Huihui Bai, Anhong Wang},
  journal={IEEE Transactions on Instrumentation and Measurement},
  volume={73},
  pages={5024214},
  year={2024},
  publisher={IEEE}
}
@inproceedings{zhang2023explainable,
  title={Explainable Unfolding Network For Joint Edge-Preserving Depth Map Super-Resolution},
  author={Zhang, Jialong and Zhao, Lijun and Zhang, Jinjing and Wang, Ke and Wang, Anhong},
  booktitle={2023 IEEE International Conference on Multimedia and Expo (ICME)},
  pages={888--893},
  year={2023},
  organization={IEEE}
}