Collect some super-resolution related papers, data and repositories.
Note this table is referenced from here
More years papers, plase check Quick navigation
| Title | Model | Published | Code | Keywords |
|---|---|---|---|---|
| Detail-Preserving Transformer for Light Field Image Super-Resolution | DPT | AAAI2022 | code | Light Field, Detail-Preserving Transformer |
| What Hinders Perceptual Quality of PSNR-oriented Methods? | DECLoss | arxiv | - | Detail Enhanced Contrastive Loss |
| SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution | SCSNet | arxiv | - | Image Colorization and Super-Resolution |
| Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution | AMSA | arxiv | - | RefSR |
| Efficient Non-Local Contrastive Attention for Image Super-Resolution | ENLCA | arxiv | - | SISR |
| Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond | - | arxiv | - | SISR, posterior Gaussian distribution, replace L1 loss |
| Scale-arbitrary Invertible Image Downscaling | AIDN | arxiv | - | Image Rescaling, Conditional Resampling Module |
| VRT: A Video Restoration Transformer | VRT | arxiv | code | VideoSR, Video Restoration Transformer, temporal mutual self attention and parallel warping |
| Fast Online Video Super-Resolution with Deformable Attention Pyramid | DAP | arxiv | - | VideoSR, fast, deformable attention pyramid |
| Revisiting RCAN: Improved Training for Image Super-Resolution | RCAN-it | arxiv | code | SISR, train tricks |
| Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence | BAIRNet | arxiv | - | Image Rescaling, be robust in cycle idempotence test |
| Disentangling Light Fields for Super-Resolution and Disparity Estimation | DistgSSR | TPAMI 2022 | code | Light Field |
| Fast Neural Architecture Search for Lightweight Dense Prediction Networks | LDP-Sup | arxiv | - | SISR, NAS, Lightweights |
| Learning the Degradation Distribution for Blind Image Super-Resolution | PDM-SR | CVPR2022 | code | blind SR, probabilistic degradation model, unpaired sr |
| Reference-based Video Super-Resolution Using Multi-Camera Video Triplets | RefVSR | CVPR2022 | code | Reference-based VSR, Multi-Camera VSR, RealMCVSR Dataset, Bidirectional recurrent framework |
| Deep Constrained Least Squares for Blind Image Super-Resolution | DCLS | CVPR2022 | code | Blind SR, a dynamic deep linear kernel, Deep Constrained Least Squares |
| Blind Image Super Resolution with Semantic-Aware Quantized Texture Prior | QuanTexSR | arxiv | code | Blind SR, Quantized Texture Prior, Semantic-Guided QTP Pretraining |
| Unfolded Deep Kernel Estimation for Blind Image Super-resolution | UDKE | arxiv | code | Blind SR, unfolded deep kernel estimation |
| Efficient Long-Range Attention Network for Image Super-resolution | ELAN | arxiv | code | SISR SOTA, efficient long-range attention block, group-wise multi-scale self-attention, better results against the transformer-based SR |
| STDAN: Deformable Attention Network for Space-Time Video Super-Resolution | STDAN | arxiv | - | VideoSR, long-short term feature interpolation, spatial-temporal deformable feature aggregation |
| Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution | ACT | arxiv | - | SISR SOTA, ViT+CNN |
| Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution | HPUN | arxiv | - | Lightweight SISR SOTA, Down-sample, Pixel-unshuffle |
| A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution | TATT | arxiv | code | Scene Text SR, CNN and Transformer, text structure consistency loss |
| ARM: Any-Time Super-Resolution Method | ARM | arxiv | code | SISR, Edge-to-PSNR lookup,tradeoff between computation overhead and performance |
| RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution | RSTT | CVPR2022 | code | VideoSR, spatialtemporal transformer |
| Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution | DASR | arxiv | code | RealSR, degradation-adaptive |
| Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling | ETDM | CVPR2022 | - | VideoSR, A novel back-and-forth refinement strategy, A new framework to explore the temporal diff LR and HR |
| C3-STISR: Scene Text Image Super-resolution with Triple Clues | C3-STISR | IJCAI2022 | code | Scene text SR |
| Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer | LBNet | IJCAI2022 | code | Lightweight SISR, Symmetric CNN, Recursive Transformer |
| Attentive Fine-Grained Structured Sparsity for Image Restoration | LBNet | CVPR2022 | code | Layer-wise N:M structured Sparsity pruning |
| A New Dataset and Transformer for Stereoscopic Video Super-Resolution | Trans-SVSR | CVPR2022 | code | Stereo video super-resolution |
| Accelerating the Training of Video Super-Resolution | - | arxiv | code | VideoSR, 6.2× speedup in wall-clock training time |
| Metric Learning based Interactive Modulation for Real-World Super-Resolution | MM-RealSR | arxiv | code | Metric Learning based Interactive Modulation |
| Activating More Pixels in Image Super-Resolution Transformer | HAT | arxiv | code | SISR,SOTA, Hybrid Attention Transformer, more than 1dB |
| SPQE: Structure-and-Perception-Based Quality Evaluation for Image Super-Resolution | - | arxiv | - | SR-IQA |
| Spatial-Temporal Space Hand-in-Hand:Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning | CycMu-Net | arxiv | code | ST-VideoSR,Cycle-Projected Mutual Learning |
| RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization | RepSR | arxiv | code | Efficient SISR, lightweight, VGG-like, Structural Re-Parameterization and Batch Normalization |
| Blueprint Separable Residual Network for Efficient Image Super-Resolution | BSRN | arxiv | code | Efficient SISR, lightweight, blueprint separable convolution |
| Evaluating the Generalization Ability of Super-Resolution Networks | SRGA | arxiv | - | Generalization Assessment Index, Patch-based Image Evaluation Set |
| Residual Local Feature Network for Efficient Super-Resolution | RLFN | arxiv | code | Efficient SISR, lightweight, Residual Local Feature Network |
| Textural-Structural Joint Learning for No-Reference Super-Resolution Image Quality Assessment | NRIQA | arxiv | code | No-Reference Super-Resolution Image Quality Assessment |
| ShuffleMixer: An Efficient ConvNet for Image Super-Resolution | ShuffleMixer | arxiv | code | Efficient SISR, lightweight, point wises MLP |
| Real-Time Super-Resolution for Real-World Images on Mobile Devices | - | arxiv | - | Efficient SISR, lightweight, 50fps |
| Real-World Image Super-Resolution by Exclusionary Dual-Learning | RWSR-EDL | arxiv | code | Dual Learning |
| Learning Trajectory-Aware Transformer for Video Super-Resolution | TTVSR | CVPR2022 oral | code | VideoSR, Trajectory-awareTransformer |
| LAR-SR: A Local Autoregressive Model for Image Super-Resolution | LAR-SR | CVPR2022 | - | GAN-based model，Autoregressive |
| Memory-Augmented Non-Local Attention for Video Super-Resolution | MANA | CVPR2022 | code | VideoSR, Memory-Augmented Attention |
| Learning Graph Regularisation for Guided Super-Resolution | - | CVPR2022 | code | graph-super-resolution |
| videoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution | VideoINR | CVPR2022 | code | ST-VideoSR,Video Implicit Neural Representation |
| Stable Long-Term Recurrent Video Super-Resolution | MRVSR | CVPR2022 | code | VideoSR, Lipschitz stability |
| Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel | BSRDM | CVPR2022 | code | Monte Carlo EM |
| Reflash Dropout in Image Super-Resolution | - | CVPR2022 | - | Dropout in sr |
| Reference-based Video Super-Resolution Using Multi-Camera Video Triplets | RefVSR | CVPR2022 | code | RefVSR |
| SphereSR: 360◦ Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation | SphereSR | CVPR2022 | - | SphereSR |
| Investigating Tradeoffs in Real-World Video Super-Resolution | RealBasicVSR | CVPR2022 | code | RealBasicVSR |
| Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites | HDR-DSP | CVPR2022 | code | Self-Supervised |
| Texture-based Error Analysis for Image Super-Resolution | - | CVPR2022 | - | Texture Embedding |
| A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution | TATT | CVPR2022 | code | Scene Text SR |
| MNSRNet: Multimodal Transformer Network for 3D Surface Super-Resolution | MNSRNet | CVPR2022 | - | 3D surface super-resolution |
| Task Decoupled Framework for Reference-based Super-Resolution | - | CVPR2022 | - | - |
| Joint Super-Resolution and Inverse Tone-Mapping:A Feature Decomposition Aggregation Network and A New Benchmark | FDAN | TIP | - | joint SR-ITM |
| Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution | CFIN | arxiv | - | SISR, Lightweight |
| Degradation-Guided Meta-Restoration Network for Blind Super-Resolution | DMSR | arxiv | - | blind SR |
| Residual Sparsity Connection Learning for Efficient Video Super-Resolution | RSCL | arxiv | - | VideoSR,Residual Sparsity Connection |
| AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos | AnimeSR | arxiv | - | Animation Video SR |
| Learning a Degradation-Adaptive Network for Light Field Image Super-Resolution | LF-DAnet | arxiv | code | Light Field SR |
| CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution | CADyQ | ECCV2022 | code | |
| Towards Interpretable Video Super-Resolution via Alternating Optimization | DAVSR | ECCV2022 | code | STVSR, Motion Blur, Motion Aliasing |
| Reference-based Image Super-Resolution with Deformable Attention Transformer | DATSR | ECCV2022 | code | RefSR, Correspondence Matching, Texture Transfer, Deformable Attention Transformer |
| Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution | SPLUT | ECCV2022 | code | SISR，look-up table, series-parallel network |
| Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution | FTVSR | ECCV2022 | code | VSR，Transformer, Frequency Learning, Compression |
| Image Super-Resolution with Deep Dictionary | SRDD | ECCV2022 | code | SISR,Deep Dictionary, Sparse Representation |
| Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution | MMSR | ECCV2022 | code | Mutual Modulation, Self-Supervised Super-Resolution, Cross-Modal, Multi-Modal |
| Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution | - | arxiv | code | SISR, Mobile Real-time，nas |
| Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network | DLV-IRN | ACMM 2022 | - | Image Rescaling |
| Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution | PDASR | arxiv | code | Perception-Distortion Trade-Off, Constrained Optimization |
| Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution | A-LIIF | ICIP2022 | code | implicit image function |
| Rethinking Alignment in Video Super-Resolution Transformers | - | arxiv | code | VSR, feature alignment |
| SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution | SwinFIR | arxiv | - | SISR, Fast Fourier Convolution，SOTA |
| KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution | KXNet | ECCV2022 | code | Blind SR, Model-Driven, Kernel Estimation, Mutual Learning |
| MULTI-SCALE ATTENTION NETWORK FOR SINGLE IMAGE SUPER-RESOLUTION | MAN | arxiv | code | SISR, CNN-based multi-scale attention, SOTA |
| From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution | ReDegNet | ECCV2022 | code | Blind SR, real world degradation |
| Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images | SRPO | ECCV2022 | - | SISR, lightweight, sharp edges and flatter areas |
| Efficient Image Super-Resolution using Vast-Receptive-Field Attention | VapSR | ECCVW 2022 | code | SISR, lightweight |
| ISTA-Inspired Network for Image Super-Resolution | ISTAR | arxiv | - | SISR, unfolding iterative shrinkage thresholding algorith |
| N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution | NGswin | arxiv | - | Lightweight SISR, N-Gram |
| RDRN: Recursively Defined Residual Network for Image Super-Resolution | RDRN | arxiv | - | SISR, Recursively |