mlsanityData to 14 Oct 2026

Blueprint Separable Residual Network for Efficient Image Super-Resolution

arXiv 2205.05996 ↗First posted 12 May 2022cs.CV eess.IVcited by 44

Not on the map. Why?

Abstract (arXiv)

Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply in edge devices. To alleviate this problem, many novel and effective solutions have been proposed. Convolutional neural network (CNN) with the attention mechanism has attracted increasing attention due to its efficiency and effectiveness. However, there is still redundancy in the convolution operation. In this paper, we propose Blueprint Separable Residual Network (BSRN) containing two efficient designs. One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation. The other is to enhance the model ability by introducing more effective attention modules. The experimental results show that BSRN achieves state-of-the-art performance among existing efficient SR methods. Moreover, a smaller variant of our model BSRN-S won the first place in model complexity track of NTIRE 2022 Efficient SR Challenge. The code is available at https://github.com/xiaom233/BSRN.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). Builds on 43 of its 58 references that are in the map. First posted on arXiv 12 May 2022.

Builds on

43 of 58 references.

References · 43

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  8. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  9. 2019Searching for MobileNetV3cited by 1,994
  10. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  11. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  12. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
31 more
  1. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  2. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  3. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  4. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  5. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  7. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  8. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  9. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 329
  10. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  11. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  12. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 264
  13. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  14. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  15. 2013Predicting Parameters in Deep Learningcited by 224
  16. 2020Residual Feature Distillation Network for Lightweight Image Super-Resolutioncited by 122
  17. 2018Fast and Accurate Single Image Super-Resolution via Information Distillation Networkcited by 121
  18. 2015Data-free parameter pruning for Deep Neural Networkscited by 112
  19. 2021LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyondcited by 88
  20. 2020Efficient Image Super-Resolution Using Pixel Attentioncited by 87
  21. 2015Fast ConvNets Using Group-wise Brain Damagecited by 82
  22. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  23. 2020DHP: Differentiable Meta Pruning via HyperNetworkscited by 57
  24. 2015Bayesian Dark Knowledgecited by 45
  25. 2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
  26. 2019Efficient Residual Dense Block Search for Image Super-Resolutioncited by 37
  27. 2020AIM 2020 Challenge on Efficient Super-Resolution: Methods and Resultscited by 36
  28. 2020Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNetscited by 28
  29. 2021Attention in Attention Network for Image Super-Resolutioncited by 20
  30. 2021Trilevel Neural Architecture Search for Efficient Single Image Super-Resolutioncited by 15
  31. 2020The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architecturescited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 9; 2024: 14; 2025: 11; 2026: 3.

44 papers.

Sort:

By area:

  1. 2022Cross Aggregation Transformer for Image Restorationcited by 92
  2. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  3. 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 57
  4. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  5. 2022EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Predictioncited by 42
  6. 2023OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformercited by 26
  7. 2025The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Reportcited by 26
  8. 2024DVMSR: Distillated Vision Mamba for Efficient Super-Resolutioncited by 24
  9. 2023Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolutioncited by 21
  10. 2024Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learningcited by 19
  11. 2023ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolutioncited by 18
  12. 2022Efficient Image Super-Resolution using Vast-Receptive-Field Attentioncited by 16
32 more
  1. 2025CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolutioncited by 16
  2. 2022Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Networkcited by 13
  3. 2022UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic Networkcited by 11
  4. 2024Infrared Image Super-Resolution via Lightweight Information Split Networkcited by 11
  5. 2024Large Kernel Distillation Network for Efficient Single Image Super-Resolutioncited by 9
  6. 2024CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolutioncited by 8
  7. 2024Accelerating Image Super-Resolution Networks with Pixel-Level Classificationcited by 8
  8. 2026Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensationcited by 6
  9. 2024MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolutioncited by 5
  10. 2023Multi-Depth Branch Network for Efficient Image Super-Resolutioncited by 4
  11. 2022Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Imagescited by 3
  12. 2024WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazingcited by 3
  13. 2024LIPT: Latency-aware Image Processing Transformercited by 3
  14. 2025Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptationcited by 3
  15. 2025Large Kernel Modulation Network for Efficient Image Super-Resolutioncited by 3
  16. 2023A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolutioncited by 2
  17. 2025Fractal-IR: A Unified Framework for Efficient and Scalable Image Restorationcited by 2
  18. 2025Enhanced Semantic Extraction and Guidance for UGC Image Super Resolutioncited by 2
  19. 2023Convolutional neural network based on sparse graph attention mechanism for MRI super-resolutioncited by 1
  20. 2023DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolutioncited by 1
  21. 2024Large coordinate kernel attention network for lightweight image super-resolutioncited by 1
  22. 2024HASN: Hybrid Attention Separable Network for Efficient Image Super-resolutioncited by 1
  23. 2025Semantic-Guided Global-Local Collaborative Networks for Lightweight Image Super-Resolutioncited by 1
  24. 2026DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolutioncited by 1
  25. 2023A High-Frequency Focused Network for Lightweight Single Image Super-Resolutioncited by 0
  26. 2024Deep Space Separable Distillation for Lightweight Acoustic Scene Classificationcited by 0
  27. 2024Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-Resolutioncited by 0
  28. 2025Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolutioncited by 0
  29. 2025High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolutioncited by 0
  30. 2025DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolutioncited by 0
  31. 2025LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolutioncited by 0
  32. 2026You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmapscited by 0