This is the official PyTorch implementation of TBSR.

Our team received 2nd place (real data track) and 3rd place (synthetic track) in NTIRE 2022 Burst Super-Resolution Challenge (CVPRW 2022).

Please see more detailed descriptions of TBSR from TBSR.pdf.

Overview of the network architecture for TBSR.

• Prerequisites

  • Python 3.x and PyTorch 1.6.
  • OpenCV, NumPy, Pillow, CuPy, tqdm, lpips, scikit-image and tensorboardX.

• Dataset

  • Please see this competition description for the download and use of datasets.

• Training

  • For track 1, modify dataroot in sh train_track1.sh and then run:

    sh train_track1.sh

  • For track 2, modify dataroot in sh train_track2.sh and then run:

    sh train_track2.sh

• Testing

  • The pre-trained models can be downloaded. You need to put the two folders in the ./ckpt/ folder.

  • For track 1, modify dataroot in sh test_track1.sh and then run:

    sh test_track1.sh

  • For track 2, modify dataroot in sh test_track2.sh and then run:

    sh test_track2.sh

• Note

  • You can specify which GPU to use by --gpu_ids, e.g., --gpu_ids 0,1, --gpu_ids 3, --gpu_ids -1 (for CPU mode). In the default setting, all GPUs are used.
  • You can refer to options for more arguments.