Large Kernel Distillation Network for Efficient Single Image Super-Resolution

Chengxing Xie, Xiaoming Zhang, Linze Li, Haiteng Meng, Tianlin Zhang, Tianrui Li, Xiaole Zhao; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 1283-1292

Abstract


Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years. One effective approach is the use of large kernel designs, which have been shown to improve the performance of SISR models while reducing their computational requirements. However, current state-of-the-art (SOTA) models still face problems such as high computational costs. To address these issues, we propose the Large Kernel Distillation Network (LKDN) in this paper. Our approach simplifies the model structure and introduces more efficient attention modules to reduce computational costs while also improving performance. Specifically, we employ the re-parameterization technique to enhance model performance without adding extra cost. We also introduce a new optimizer from other tasks to SISR, which improves training speed and performance. Our experimental results demonstrate that LKDN outperforms existing lightweight SR methods and achieves SOTA performance.

Related Material


[pdf]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Chengxing and Zhang, Xiaoming and Li, Linze and Meng, Haiteng and Zhang, Tianlin and Li, Tianrui and Zhao, Xiaole}, title = {Large Kernel Distillation Network for Efficient Single Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {1283-1292} }