dslisleedh/btc

BTC: B-spline Texture Coefficients Estimator for Screen Content Image Super-Resolution

B-spline Texture Coefficients Estimator for Screen Content Image Super-Resolution

This repoository is the official pytorch implementation of BTC introduced by:

B-spline Texture Coefficients Estimator for Screen Content Image Super-Resolution (CVPR 2023, Highlight)

Environment

• Python 3
• Pytorch 1.13.0
• TensorboardX
• pyyaml, numpy, tqdm, imageio

Demo

1. Download a SCI1K pre-trained model: RDN-BTC

2. For demo, python demo.py --input [INPUT] --model [MODEL] --scale [SCALE] --output output.png --gpu [GPU]

• [INPUT] : input image's path (e.g. --input input.png).
• [MODEL] : to define the pre-trained model (e.g. --model rdn+btc-3rd.pth).
• [SCALE] : arbitrary magnification (e.g. --scale 3 or --scale 6.4).
• [GPU] : to specify the GPUS (e.g. --gpu 0).

Dataset

1. mkdir ../Data for putting the dataset folders.

2. cd ../Data and download the datasets (SCI1K, SCID, and SIQAD) from this repo.

3. For the additional benchmarks in Tab 6, follow Data instruction provided by this repo.

Train & Test

• Train : python train.py --config configs/train/[TRAIN_CONFIG] --gpu [GPU]

  • [TRAIN_CONFIG] : to define model configuration (e.g. train-rdn+btc-3rd.yaml).
  • [GPU] : to specify the GPUS (e.g. --gpu 0 or --gpu 0,1).

• Test : python test.py --config configs/test/[TEST_CONFIG] --model save/[MODEL] --gpu [GPU]

  • [TEST_CONFIG] : to define test configuration (e.g. test-sci1k-02.yaml for SCI1K dataset on x2).
  • [MODEL] : to define the pre-trained model (e.g. rdn+btc-3rd/epoch_last.pth).
  • [GPU] : to specify the GPUS (e.g. --gpu 0 or --gpu 0,1).

Acknowledgements

This code is built on LIIF and LTE. We thank the authors for sharing their codes.