lastbasket / Polarization-Prompt-Fusion-Tuning

CVPR 2024: Robust Depth Enhancement via Polarization Prompt Fusion Tuning

CVPR 2024 - Robust Depth Enhancement via Polarization Prompt Fusion Tuning

Kei Ikemura · Yiming Huang · Felix Heide
Zhaoxiang Zhang · Qifeng Chen · Chenyang Lei

|| Paper || Project Page ||

0. Todo

• Complete environment setup instruction.
• Provide dataset download link and pre-processing utilities.
• Provide model checkpoints and inference instruction.
• Provide custom training instruction.
• Provide custom evaluation instruction

1. Setting-Up Environment

Coming soon...

2. Dataset

Coming soon...

3. Model Checkpoints

Coming soon...

4. Training

Coming soon...

5. Inference & Evaluation

Coming soon...

6. Acknowledgement

This work was supported by the InnoHK program.

In addition, we thank Zhang et al. who kindly open-sourced their code-base to the CompletionFormer model, which has been the foundation of our research as well as the code.

7. Cite

@misc{ikemura2024robust,
    title={Robust Depth Enhancement via Polarization Prompt Fusion Tuning},
    author={Kei Ikemura and Yiming Huang and Felix Heide and Zhaoxiang Zhang and Qifeng Chen and Chenyang Lei},
    year={2024},
    eprint={2404.04318},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}