Skip to content

Latest commit

 

History

History
87 lines (57 loc) · 4.99 KB

README.md

File metadata and controls

87 lines (57 loc) · 4.99 KB

TTSR (CVPR'2020)

Learning Texture Transformer Network for Image Super-Resolution

Task: Image Super-Resolution

Abstract

We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image. Recent progress has been made by taking high-resolution images as references (Ref), so that relevant textures can be transferred to LR images. However, existing SR approaches neglect to use attention mechanisms to transfer high-resolution (HR) textures from Ref images, which limits these approaches in challenging cases. In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively. TTSR consists of four closely-related modules optimized for image generation tasks, including a learnable texture extractor by DNN, a relevance embedding module, a hard-attention module for texture transfer, and a soft-attention module for texture synthesis. Such a design encourages joint feature learning across LR and Ref images, in which deep feature correspondences can be discovered by attention, and thus accurate texture features can be transferred. The proposed texture transformer can be further stacked in a cross-scale way, which enables texture recovery from different levels (e.g., from 1x to 4x magnification). Extensive experiments show that TTSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations.

Results and models

Evaluated on CUFED dataset (RGB channels), scale pixels in each border are cropped before evaluation. The metrics are PSNR and SSIM .

Model Dataset scale PSNR SSIM Training Resources Download
ttsr-rec_x4_c64b16_g1_200k_CUFED CUFED x4 25.2433 0.7491 1 (TITAN Xp) model | log
ttsr-gan_x4_c64b16_g1_500k_CUFED CUFED x4 24.6075 0.7234 1 (TITAN Xp) model | log

Quick Start

Train

Train Instructions

You can use the following commands to train a model with cpu or single/multiple GPUs.

# cpu train
CUDA_VISIBLE_DEVICES=-1 python tools/train.py configs/ttsr/ttsr-gan_x4c64b16_1xb9-500k_CUFED.py

# single-gpu train
python tools/train.py configs/ttsr/ttsr-gan_x4c64b16_1xb9-500k_CUFED.py

# multi-gpu train
./tools/dist_train.sh configs/ttsr/ttsr-gan_x4c64b16_1xb9-500k_CUFED.py 8

For more details, you can refer to Train a model part in train_test.md.

Test

Test Instructions

You can use the following commands to test a model with cpu or single/multiple GPUs.

# cpu test
CUDA_VISIBLE_DEVICES=-1 python tools/test.py configs/ttsr/ttsr-gan_x4c64b16_1xb9-500k_CUFED.py https://download.openmmlab.com/mmediting/restorers/ttsr/ttsr-gan_x4_c64b16_g1_500k_CUFED_20210626-2ab28ca0.pth

# single-gpu test
python tools/test.py configs/ttsr/ttsr-gan_x4c64b16_1xb9-500k_CUFED.py https://download.openmmlab.com/mmediting/restorers/ttsr/ttsr-gan_x4_c64b16_g1_500k_CUFED_20210626-2ab28ca0.pth

# multi-gpu test
./tools/dist_test.sh configs/ttsr/ttsr-gan_x4c64b16_1xb9-500k_CUFED.py https://download.openmmlab.com/mmediting/restorers/ttsr/ttsr-gan_x4_c64b16_g1_500k_CUFED_20210626-2ab28ca0.pth 8

For more details, you can refer to Test a pre-trained model part in train_test.md.

Citation

@inproceedings{yang2020learning,
  title={Learning texture transformer network for image super-resolution},
  author={Yang, Fuzhi and Yang, Huan and Fu, Jianlong and Lu, Hongtao and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={5791--5800},
  year={2020}
}