【深度学习笔记】超分辨率方向相关论文汇总【偶尔更新】

• 说明：除了超分领域的论文外，同时也会附加一些backbone网络或者building block、去噪（Denoise）、去雾（Dehaze）、去雨（Derain）去模糊（Deblur）、修复（Restoration）等对超分领域有启发的相关领域论文！
• 我自己是一枚科研小白，熬肝整理，希望能给大家一些帮助，如果各路大神有比较好的见解、相关资料等等，欢迎在评论区补充，多多交流！

标题	来源&时间	方向	源码	状态	推荐指数	相关资料
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks	ECCV 2020	注意力机制	无	未读	8.5	与SENet互补提升，华为诺亚提出自注意力新机制：Weight Excitation
	时间	方向	源	√	分数	资料
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks	arXiv 2020	知识蒸馏	MEAL-V2	未读	分数	无需额外数据、Tricks、架构调整，CMU开源首个将ResNet50精度提升至80%+新方法
Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification	2020.09.22	模型鲁棒性	无	未读	8	【正交球面正则化】让模型不偏不倚更加鲁棒的简单粗暴神器，推荐阅读和使用！！！
Learning Image-adaptive 3D Lookup Tables for High Performance Photo enhancement in Real-time	2020	图像增强	3DLUT	未读	8	图像增强领域大突破！以1.66ms的速度处理4K图像，港理工提出图像自适应的3DLUT
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations	CVPR 2018	适用于多种退化模型的单个超分模型	有	√	8.5	1，2
Spatial Transformer Networks	NIPS 2015	平移不变性	torch	未读	8	详细解读Spatial Transformer Networks（STN）
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks	ICML 2019	网络架构设计	PyTorch Tensorflow	√	8.5	简短的翻译
Image Super-Resolution via Dual-State Recurrent Networks	CVPR 2018	双状态递归超分	DSRN	√	8	相关资料
Multi-scale Residual Network for Image Super-Resolution	ECCV 2018	适用于多个scale的单个超分模型	MSRN	√	8.5
Invertible Image Rescaling	ECCV 2020	可逆的图像缩放、高低频信息的分离和利用	IRN	√	8.5	ECCV 2020 Oral·可逆图像缩放：完美恢复降采样后的高清图片
Single Image Super-Resolution via a Holistic Attention Network	ECCV 2020	整体注意力机制	无	√	9	ECCV2020最新图像超分辨重建文章
A Deep Journey into Super-resolution：A Survey	ACM Computing Surveys 2020	CNN-based SISR综述	无	√	8.5	资料
Brief Survey of Single Image Super-Resolution Reconstruction Based on Deep Learning Approaches	2020	CNN-based SISR综述	无	√	8.5	资料
Deep Learning for Image Super-resolution：A Survey	IEEE TPAMI 2020	CNN-based SISR综述	无	√	8.5	资料
A Survey of Image Super Resolution Based on CNN	2020	CNN-based SISR综述	无	√	8.5	资料
Deep Learning for Image Super-resolution：A Survey	2020	CNN-based SISR综述	无	√	8.5	资料
Deep Learning Based Single Image Super-resolution：A Survey	2019	CNN-based SISR综述	无	√	8.5	资料
Deep learning for single image super-resolution：A brief review	2019	CNN-based SISR综述	无	√	8.5	资料
ResNeSt- Split-Attention Networks	2020	网络架构设计	ResNeSt	√	8	【论文笔记】张航和李沐等提出：ResNeSt: Split-Attention Networks（ResNet改进版本）
Single Image Super-Resolution via Residual Neuron Attention Networks	2020	RNAN、注意力	无	√	8.5	资料
Learning with Privileged Information for Efficient Image Super-Resolution	ECCV 2020	PISR、基于知识蒸馏的超分	PISR	√	8	[ECCV2020] PISR - 把蒸馏Distillation成功应用到超分任务
Dynamic Convolutions- Exploiting Spatial Sparsity for Faster Inference	CVPR 2020	动态卷积	dynconv	√	8	资料
Rethinking Data Augmentation for Image Super-resolution- A Comprehensive Analysis and a New Strategy	CVPR 2020	专用与超分领域的DA	cutblur	√	8.5	资料
Learning Texture Transformer Network for Image Super-Resolution	CVPR 2020	TTSR、纹理迁移	TTSR	√	8	资料
Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining	CVPR 2020	CL-NL注意力	CL-NL	√	8.5	资料
Explorable Super Resolution	CVPR 2020	超分	开源	√	7.8	资料
Residual Feature Aggregation Network for Image Super-Resolution	CVPR 2020	RFANet、空间域注意力	无	√	8.5	资料
Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution	CVPR 2020	DSR、通道域注意力、深度图超分	无	√	8.5	资料
Deep Iterative Residual Convolutional Network for Single Image Super-Resolution	arXiv 2020	迭代残差	无	√	8	资料
Attention Cube Network for Image Restoration	ACM MM 2020	A-CubeNet、立体注意力机制	无	√	8.5	资料
Gcnet- Non-local networks meet squeeze-excitation networks and beyond	ICCVW 2019	Gcnet、NL注意力	GCNet	√	8	GCNet：当Non-local遇见SENet
Feedback Network for Image Super-Resolution	CVPR 2019	SRFBN、反馈机制	SRFBN	√	8.5	资料SRFBN的PyTorch实现
Selective Kernel Networks	CVPR 2019	SKNet、注意力	SKNet	√	7.9	资料
Second-order attention network for single image super-resolution	CVPR 2019	SAN、二阶注意力机制	SAN	√	8	资料
Residual Non-local Attention Networks for Image Restoration	ICLR 2019	RNAN、NL注意力、图像修复	无	√	8.5	资料Residual Non-local Attention Networks for Image Restoration
NASNet- A Neuron Attention Stage-by-Stage Net for Single Image Deraining	2019	NASNet、多阶段神经元注意力机制、去雨	无	√	8.5	资料
Lightweight Image Super-Resolution with Information Multi-distillation Network	ACM MM 2019	IMDN、通道分裂、轻量	IMDN	√	8	资料
Hybrid Residual Attention Network for Single Image Super Resolution	IEEE Access 2019	HRAN、残差、注意力	HRAN	√	8	资料
DANet- Dual Attention Network for Scene Segmentation	2019 CVPR	DANet、注意力、语义分割	DANet	√	8	资料
Efficient Single Image Super-Resolution via Hybrid Residual Feature Learning with Compact Back-Projection Network	CVPRW 2019	CBPN、反向投影	无	√	7	无
Bag of Tricks for Image Classification with Convolutional Neural Networks	2018	训练技巧	Bag of Tricks	√	8.5	【模型性能杀器解读】如果项目的模型遇到瓶颈，用这些Tricks就对了！！！
Wide Activation for Efficient and Accurate Image Super-Resolution	2018	WDSR、宽、残差	WDSR	√	8.5	资料
Residual dense network for image super-resolution	CVPR 2018	RDN、残差、稠密连接	RDN	√	8	资料
Image Super-Resolution Using Very Deep Residual Channel Attention Networks	ECCV 2018	RCAN、通道注意力	RCAN	√	8.5	资料
RAM- Residual Attention Module for Single Image Super-Resolution	2018	RAM、注意力	无	√	8.5	资料
PSANet：Point-wise Spatial Attention Network for Scene Parsing	ECCV 2018	PSANet、空间注意力	PSANet	√	8	资料
Non-local recurrent network for image restoration	NIPS 2018	NLRN、NL注意力	NLRN	√	8.5	资料
Non-local Neural Networks	2018	NLNet、NL注意力	NLNet	√	8.5	资料
Fast and accurate image super-resolution with deep laplacian pyramid networks	2018	MS-LapSRN、拉普拉斯金字塔	MS-LapSRN	√	8	资料
Fast and Accurate Single Image Super-Resolution via Information Distillation Network	CVPR 2018	IDN、轻量	IDN	√	8	资料
Deep back-projection networks for super-resolution	CVPR 2018	D-DBPN、反向投影	D-DBPN	√	8.5	资料
Deep Back-Projection Networks for Single Image Super-resolution	2020	方向	源	√	分数	资料
Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution	2018	CSAR、注意力	无	√	8.5	资料
CBAM- Convolutional Block Attention Module	ECCV 2018	CBAM、注意力	CBAM	√	9	资料
Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network	ECCV 2018	CARN、级联、轻量	CARN	√	8	资料
BAM- Bottleneck Attention Module	BMVC 2018	BAM、注意力	BAM	√	8.5	资料
A^2-Nets- Double Attention Networks	NIPS 2018	A^2-Nets、双注意力	A2-Nets	√	8	【文献阅读01】A2-Nets: Double Attention Networks、 【文献阅读02】A2-Nets: Double Attention Networks
	时间	方向	源	√	分数	资料