Home

Awesome

AdaBM

This repository includes the official implementation of the paper AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution (CVPR2024).

<!-- [arXiv](TBD) | [BibTeX](#bibtex) --> <!-- <p align="center"> <img src=assets/results.gif /> </p> --> <p align="center"> <img src=assets/cover_adabm.png /> </p>

Requirements

A suitable conda environment named adabm can be created and activated with:

conda env create -f environment.yaml
conda activate adabm

Preparation

Dataset

datasets
  -DIV2K
    - DIV2K_train_LR_bicubic # for training
    - DIV2K_train_HR
    - test2k # for testing
    - test4k
    - test8k
  -benchmark # for testing

Pretrained Models

Please download the pretrained models from here and place them in pretrained_model.

Usage

How to train

sh run.sh edsr 0 6 8 # gpu_id a_bit w_bit 
sh run.sh edsr 0 4 4 # gpu_id a_bit w_bit 

How to test

sh run.sh edsr_eval 0 6 8 # gpu_id a_bit w_bit 
sh run.sh edsr_eval 0 4 4 # gpu_id a_bit w_bit

More running scripts can be found in run.sh.

Comments

Our implementation is based on EDSR(PyTorch).

Coming Soon...

BibTeX

If you found our implementation useful, please consider citing our paper:

@misc{hong2024adabm,
      title={AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution}, 
      author={Cheeun Hong and Kyoung Mu Lee},
      year={2024},
      eprint={2404.03296},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Contact

Email: cheeun914@snu.ac.kr