Lightweight image super-resolution with enhanced CNN

8 Jul 2020  ·  Chunwei Tian, Ruibin Zhuge, Zhihao Wu, Yong Xu, WangMeng Zuo, Chen Chen, Chia-Wen Lin ·

Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts of convolutions and parameters usually consume high computational cost and more memory storage for training a SR model, which limits their applications to SR with resource-constrained devices in real world. To resolve these problems, we propose a lightweight enhanced SR CNN (LESRCNN) with three successive sub-blocks, an information extraction and enhancement block (IEEB), a reconstruction block (RB) and an information refinement block (IRB). Specifically, the IEEB extracts hierarchical low-resolution (LR) features and aggregates the obtained features step-by-step to increase the memory ability of the shallow layers on deep layers for SISR. To remove redundant information obtained, a heterogeneous architecture is adopted in the IEEB. After that, the RB converts low-frequency features into high-frequency features by fusing global and local features, which is complementary with the IEEB in tackling the long-term dependency problem. Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image. The proposed LESRCNN can obtain a high-quality image by a model for different scales. Extensive experiments demonstrate that the proposed LESRCNN outperforms state-of-the-arts on SISR in terms of qualitative and quantitative evaluation. The code of LESRCNN is accessible on https://github.com/hellloxiaotian/LESRCNN.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution Set14 - 4x upscaling LESRCNN PSNR 28.44 # 45
SSIM 0.7772 # 49
Image Super-Resolution Set14 - 4x upscaling LESRCNN-S PSNR 28.43 # 46
SSIM 0.7776 # 47

Methods


No methods listed for this paper. Add relevant methods here