| SRCNN | 3-layer convolutional network | ECCV | 2014 |
| CSCN | sparse coding and deep learning | ICCV | 2015 |
| FSRCNN | transposed convolution | ECCV | 2016 |
| ESPCN | efficient sub-pixel convolution | CVPR | 2016 |
| VDSR | deep networks | CVPR | 2016 |
| DRCN | recursive CNN | CVPR | 2016 |
| EDSR | removing the Batch Normalization layer in the residual block | CVPR | 2017 |
| LapSRN | progressively reconstruct the sub-band | CVPR | 2017 |
| DRRN | Deep Recursive Residual Network | CVPR | 2017 |
| SRDenseNet | DenseNet | ICCV | 2017 |
| MemNet | memory block, consisting of a recursive unit and a gate unit | ICCV | 2017 |
| RDN | combining residuals and dense connections | CVPR | 2018 |
| DSRN | Dual-State Recurrent Networks | CVPR | 2018 |
| SRMDNF | a Single Convolutional Super-Resolution Network for Multiple Degradations | CVPR | 2018 |
| IDN | information distillation blocks | CVPR | 2018 |
| DBPN | iterative up- and down- sampling layers | CVPR | 2018 |
| ZSSR | examples extracted solely from the input image itself | CVPR | 2018 |
| CARN | cascading mechanism upon a residual network | ECCV | 2018 |
| RCAN | Residual Channel Attention Networks | ECCV | 2018 |
| MSRN | Multi-scale Residual Network | ECCV | 2018 |
| IMDN | cascaded information multi-distillation blocks | ACMMM | 2019 |
| SRFBN | feedback network | CVPR | 2019 |
| OISR | ordinary differential equation (ODE)-inspired design scheme | CVPR | 2019 |
| META-SR | arbitrary SR | CVPR | 2019 |
| SAN | second-order attention network | CVPR | 2019 |
| RNAN | local and non-local attention blocks | ICLR | 2019 |
| EBRN | Embedded Block Residual Network | ICCV | 2019 |
| SCN | pyramid representation via bilinear down-scaling | AAAI | 2020 |
| MZSR | Meta-Transfer Learning | CVPR | 2020 |
| DRN | dual regression scheme to reduce space of the possible functions | CVPR | 2020 |
| cutBlur | data preprocessing | CVPR | 2020 |
| CSNLN | Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining | CVPR | 2020 |
| RFANet | residual feature aggregation | CVPR | 2020 |
| HAN | layer attention module (LAM) and a channel-spatial attention module (CSAM) | ECCV | 2020 |
| IRN | Invertible Rescaling Net | ECCV | 2020 |
| LatticeNet | two butterfly structures are applied to combine two RBs | ECCV | 2020 |
| ClassSR | combined classification and SR in a unified framework | CVPR | 2021 |
| FKP | normalizing flow-based kernel prior (FKP) for kernel modeling | CVPR | 2021 |
| SRWrap | arbitrary image transformation | CVPR | 2021 |
| NLSA | dynamic sparse attention pattern | CVPR | 2021 |
| LUT | precomputed HR output values from the table | CVPR | 2021 |
| SMSR | sparse masks, sparse convolution | CVPR | 2021 |
| AdderSR | adder networks | CVPR | 2021 |
| FAD | frequency-aware dynamic network, DCT | ICCV | 2021 |
| DFSA | learning of high frequency features both locally and globally | ICCV | 2021 |
| ArbRCAN | scale-arbitrary SR | ICCV | 2021 |
| NAPS | NAS, pruning | ICCV | 2021 |
| CRAN | Context Reasoning Attention Network | ICCV | 2021 |
| LIIF | implicit neural representation | CVPR | 2021 |
| DCLS | deconvolution module, channel-wise deblurring | CVPR | 2022 |
| SLS | pruning method | CVPR | 2022 |
| LTE | dominant-frequency estimator | CVPR | 2022 |
| SESR | over-parameterize | MLS | 2022 |
| SPLUT | Series-Parallel Lookup Tables | ECCV | 2022 |
| HPUN | efficient and effective downsampling module | arxiv | 2022 |
| CMOS | multi modalities combination | CVPR | 2023 |
| CABM | bit mapping | CVPR | 2023 |
| LINF | normalizing flow | CVPR | 2023 |
| ETDS | lightweight sr | CVPR | 2023 |
| MSSR | scalable sr | CVPR | 2023 |
| SUDF | frequency-based sr | CVPR | 2023 |