- π [2025εΉ΄03ζ27ζ₯] Paper preprint released!
- π [2025εΉ΄06ζ26ζ₯] Our paper has been accepted to ICCV 2025!
- πΎ [2025εΉ΄06ζ30ζ₯] Codebase and model checkpoints are now available.
- Python 3.9
- PyTorch 2.0.1
git clone https://github.com/LabShuHangGU/CTMSR.git conda create -n ctmsr python=3.9 conda activate ctmsr pip install -r requirements.txt python setup.py develop
- Download the training dataset ImageNet and put them in the folder
./datasets.
- Refer to the training configuration files in
./options/trainfolder for detailed settings.
Γγ°γ€ 8 (per GPU) CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --use-env --nproc_per_node=4 --master_port=1145 basicsr/train.py -opt options/train/ctmsr_train.yml --launcher pytorch">
# batch size = 4 (GPUs) Γγ°γ€ 8 (per GPU)
CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --use-env --nproc_per_node=4 --master_port=1145 basicsr/train.py -opt options/train/ctmsr_train.yml --launcher pytorch- Download and generate the testing data (ImageNet-Test + RealSR + RealSet65) and put them in the folder
./datasets.
- Download the pretrained models and put them in the folder
./experiments/pretrained_models.
- Refer to the testing configuration files in
./options/testfolder for detailed settings.
CUDA_VISIBLE_DEVICES=0 python basicsr/test.py -opt options/test/ctmsr_test.yml
@InProceedings{You_2025_ICCV,
author = {You, Weiyi and Zhang, Mingyang and Zhang, Leheng and Zhou, Xingyu and Shi, Kexuan and Gu, Shuhang},
title = {Consistency Trajectory Matching for One-Step Generative Super-Resolution},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2025},
pages = {12747-12756}
}