Lightweight Image Super-Resolution with Enhanced CNN（LESRCNN）is conducted by Chunwei Tian, Ruibin Zhuge, Zhihao Wu, Yong Xu, Wangmeng Zuo, Chen Chen and Chia-Wen Lin, and accepted by Knowledge-Based Systems (IF:8.038) in 2020. It is implemented by Pytorch. And it is reported by Cver and 52CV. Its website is https://mp.weixin.qq.com/s/njlAEQXxjXKqFcxM7KYiqA.
This paper uses a flexible sub-pixel convolutional technique for image blind super-resolution, which is useful for phones and cameras. Also, it has less parameters and faster super-resolution speed.
Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts ofconvolutions and parameters usually consume high computational cost and more memory storagefor training a SR model, which limits their applications to SR with resource-constrained devicesin 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 fordifferent scales. Extensive experiments demonstrate that the proposed LESRCNN outperforms state-of-the-arts on SISR in terms of qualitative and quantitative evaluation.
The training dataset is downloaded at https://pan.baidu.com/s/1uqdUsVjnwM_6chh3n46CqQ （secret code：auh1）(baiduyun) or https://drive.google.com/file/d/1TNZeV0pkdPlYOJP1TdWvu5uEroH-EmP8/view (google drive)
The test dataset of Set5 is downloaded at 链接：https://pan.baidu.com/s/1YqoDHEb-03f-AhPIpEHDPQ (secret code：atwu) (baiduyun) or https://drive.google.com/file/d/1hlwSX0KSbj-V841eESlttoe9Ew7r-Iih/view?usp=sharing (google drive)
The test dataset of Set14 is downloaded at 链接：https://pan.baidu.com/s/1GnGD9elL0pxakS6XJmj4tA (secret code：vsks) (baiduyun) or https://drive.google.com/file/d/1us_0sLBFxFZe92wzIN-r79QZ9LINrxPf/view?usp=sharing (google drive)
The test dataset of B100 is downloaded at 链接：https://pan.baidu.com/s/1GV99jmj2wrEEAQFHSi8jWw （secret code：fhs2) (baiduyun) or https://drive.google.com/file/d/1G8FCPxPEVzaBcZ6B-w-7Mk8re2WwUZKl/view?usp=sharing (google drive)
The test dataset of Urban100 is downloaded at 链接：https://pan.baidu.com/s/15k55SkO6H6A7zHofgHk9fw (secret code：2hny) (baiduyun) or https://drive.google.com/file/d/1yArL2Wh79Hy2i7_YZ8y5mcdAkFTK5HOU/view?usp=sharing (google drive)
python x2/train.py --patch_size 64 --batch_size 64 --max_steps 600000 --decay 400000 --model lesrcnn --ckpt_name lesrcnn_x2 --ckpt_dir checkpoint/lesrcnn_x2 --scale 2 --num_gpu 1
python x3/train.py --patch_size 64 --batch_size 64 --max_steps 600000 --decay 400000 --model lesrcnn --ckpt_name lesrcnn_x3 --ckpt_dir checkpoint/lesrcnn_x3 --scale 3 --num_gpu 1
python x4/train.py --patch_size 64 --batch_size 64 --max_steps 600000 --decay 400000 --model lesrcnn --ckpt_name lesrcnn_x4 --ckpt_dir checkpoint/lesrcnn_x4 --scale 4 --num_gpu 1
python lesrcnn_b/train.py --patch_size 64 --batch_size 64 --max_steps 600000 --decay 400000 --model lesrcnn --ckpt_name lesrcnn --ckpt_dir checkpoint/lesrcnn --scale 0 --num_gpu 1
python x2/tcw_sample.py --model lesrcnn --test_data_dir dataset/Urban100 --scale 2 --ckpt_path ./x2/lesrcnn_x2.pth --sample_dir samples_singlemodel_urban100_x2
python x3/tcw_sample.py --model lesrcnn --test_data_dir dataset/Urban100 --scale 3 --ckpt_path ./x3/lesrcnn_x3.pth --sample_dir samples_singlemodel_urban100_x3
python x4/tcw_sample.py --model lesrcnn --test_data_dir dataset/Urban100 --scale 4 --ckpt_path ./x4/lesrcnn_x4.pth --sample_dir samples_singlemodel_urban100_x4
python lesrcnn_b/tcw_sample_b.py --model lesrcnn --test_data_dir dataset/Urban100 --scale 2 --ckpt_path lesrcnn_b/lesrcnn.pth --sample_dir samples_singlemodel_urban100_x2
python lesrcnn_b/tcw_sample_b.py --model lesrcnn --test_data_dir dataset/Urban100 --scale 3 --ckpt_path lesrcnn_b/lesrcnn.pth --sample_dir samples_singlemodel_urban100_x3
python lesrcnn_b/tcw_sample_b.py --model lesrcnn --test_data_dir dataset/Urban100 --scale 4 --ckpt_path lesrcnn_b/lesrcnn.pth --sample_dir samples_singlemodel_urban100_x4
