mlsanityData to 7 Oct 2026

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond

arXiv 2105.10422 ↗First posted 21 May 2021cs.CVcited by 88

Not on the map. Why?

Abstract (arXiv)

Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. Last few years have witnessed impressive progress propelled by deep learning methods. However, one critical challenge faced by existing methods is to strike a sweet spot of deep model complexity and resulting SISR quality. This paper addresses this pain point by proposing a linearly-assembled pixel-adaptive regression network (LAPAR), which casts the direct LR to HR mapping learning into a linear coefficient regression task over a dictionary of multiple predefined filter bases. Such a parametric representation renders our model highly lightweight and easy to optimize while achieving state-of-the-art results on SISR benchmarks. Moreover, based on the same idea, LAPAR is extended to tackle other restoration tasks, e.g., image denoising and JPEG image deblocking, and again, yields strong performance. The code is available at https://github.com/dvlab-research/Simple-SR.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Builds on 31 of its 57 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

31 of 57 references.

References · 31

  1. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  3. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  6. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  7. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  8. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  9. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  10. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  11. 2016Dynamic Filter Networkscited by 318
  12. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
19 more
  1. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 263
  2. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  3. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  4. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
  5. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  6. 2017Video Frame Synthesis using Deep Voxel Flowcited by 209
  7. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 180
  8. 2017Video Frame Interpolation via Adaptive Convolutioncited by 158
  9. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  10. 2019Feedback Network for Image Super-Resolutioncited by 155
  11. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  12. 2019Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Searchcited by 66
  13. 2016Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networkscited by 46
  14. 2018A Fully Progressive Approach to Single-Image Super-Resolutioncited by 46
  15. 2016RAISR: Rapid and Accurate Image Super Resolutioncited by 27
  16. 2019Lightweight Image Super-Resolution with Adaptive Weighted Learning Networkcited by 16
  17. 2017BLADE: Filter Learning for General Purpose Computational Photographycited by 12
  18. 2016Towards Deep Compositional Networkscited by 3
  19. 2017Spatially-Adaptive Filter Units for Deep Neural Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 18; 2023: 23; 2024: 18; 2025: 16; 2026: 4.

88 papers.

Sort:

By area:

  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  2. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  3. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  4. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 79
  5. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
  6. 2021On Efficient Transformer-Based Image Pre-training for Low-Level Visioncited by 64
  7. 2024Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionarycited by 63
  8. 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 56
  9. 2022Blueprint Separable Residual Network for Efficient Image Super-Resolutioncited by 44
  10. 2022ShuffleMixer: An Efficient ConvNet for Image Super-Resolutioncited by 44
  11. 2024MaIR: A Locality- and Continuity-Preserving Mamba for Image Restorationcited by 43
  12. 2021Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolutioncited by 29
38 more
  1. 2022Multi-scale Attention Network for Single Image Super-Resolutioncited by 29
  2. 2023NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXercited by 29
  3. 2025Progressive Focused Transformer for Single Image Super-Resolutioncited by 25
  4. 2021Revisiting Temporal Alignment for Video Restorationcited by 24
  5. 2023Swift Parameter-free Attention Network for Efficient Super-Resolutioncited by 24
  6. 2022Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformercited by 22
  7. 2024Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learningcited by 19
  8. 2023SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolutioncited by 18
  9. 2022Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolationcited by 17
  10. 2022Adaptive Patch Exiting for Scalable Single Image Super-Resolutioncited by 16
  11. 2022Cross-receptive Focused Inference Network for Lightweight Image Super-Resolutioncited by 16
  12. 2022Efficient Image Super-Resolution using Vast-Receptive-Field Attentioncited by 16
  13. 2021Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulationcited by 15
  14. 2023CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Inputcited by 15
  15. 2022Towards Lightweight Super-Resolution with Dual Regression Learningcited by 13
  16. 2022Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Networkcited by 13
  17. 2023DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolutioncited by 13
  18. 2024Transforming Image Super-Resolution: A ConvFormer-based Efficient Approachcited by 13
  19. 2023Learning from History: Task-agnostic Model Contrastive Learning for Image Restorationcited by 11
  20. 2025CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inferencecited by 11
  21. 2023Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolutioncited by 10
  22. 2024Activating Wider Areas in Image Super-Resolutioncited by 10
  23. 2023Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategycited by 9
  24. 2024Large Kernel Distillation Network for Efficient Single Image Super-Resolutioncited by 9
  25. 2022Efficient Meta-Tuning for Content-aware Neural Video Deliverycited by 8
  26. 2022From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolutioncited by 8
  27. 2023Real-time 6K Image Rescaling with Rate-distortion Optimizationcited by 6
  28. 2023From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigmcited by 6
  29. 2023Fully 1×1 Convolutional Network for Lightweight Image Super-Resolutioncited by 6
  30. 2023Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolutioncited by 6
  31. 2024Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolutioncited by 6
  32. 2024Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolutioncited by 5
  33. 2023Efficient Mixed Transformer for Single Image Super-Resolutioncited by 4
  34. 2023Multi-Depth Branch Network for Efficient Image Super-Resolutioncited by 4
  35. 2025An Efficient and Mixed Heterogeneous Model for Image Restorationcited by 4
  36. 2025PromptSR: Cascade Prompting for Lightweight Image Super-Resolutioncited by 4
  37. 2025Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulationcited by 4
  38. 2022DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attentioncited by 3

50 most cited of 88 All 88 (JSON)