mlsanityData to 7 Oct 2026

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

arXiv 1609.05158 ↗First posted 16 Sep 2016cs.CV stat.MLcited by 1,199

Not on the map. Why?

Cited by 78 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly bicubic interpolation, before reconstruction. This means that the super-resolution (SR) operation is performed in HR space. We demonstrate that this is sub-optimal and adds computational complexity. In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. To achieve this, we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. By doing so, we effectively replace the handcrafted bicubic filter in the SR pipeline with more complex upscaling filters specifically trained for each feature map, whilst also reducing the computational complexity of the overall SR operation. We evaluate the proposed approach using images and videos from publicly available datasets and show that it performs significantly better (+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude faster than previous CNN-based methods.

Key facts. Cited by 1,199 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 212; 2022: 226; 2023: 224; 2024: 222; 2025: 197; 2026: 117.

1,199 papers.

Sort:

By area:

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  3. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  4. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  5. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  7. 2022Simple Baselines for Image Restorationcited by 701
  8. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  9. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  10. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  11. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  12. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
38 more
  1. 2021NeRV: Neural Representations for Videoscited by 255
  2. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  3. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 226
  4. 2022VRT: A Video Restoration Transformercited by 219
  5. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  6. 2021Vision Transformers are Robust Learnerscited by 208
  7. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 202
  8. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  9. 2025GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Drivingcited by 178
  10. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 177
  11. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  12. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  13. 2025Cosmos-Reason1: From Physical Common Sense To Embodied Reasoningcited by 159
  14. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  15. 2021Transformer for Single Image Super-Resolutioncited by 150
  16. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 149
  17. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  18. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 137
  19. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  20. 2021Local Texture Estimator for Implicit Representation Functioncited by 126
  21. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  22. 2021XVFI: eXtreme Video Frame Interpolationcited by 123
  23. 2021Video Frame Interpolation Transformercited by 122
  24. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  25. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  26. 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformerscited by 116
  27. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  28. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  29. 2022Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generationcited by 106
  30. 2021Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understandingcited by 97
  31. 2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 97
  32. 2023Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolationcited by 97
  33. 2023Identity-Preserving Talking Face Generation with Landmark and Appearance Priorscited by 97
  34. 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 96
  35. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  36. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 92
  37. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  38. 2022Cross Aggregation Transformer for Image Restorationcited by 92

50 most cited of 1,199 All 1,199 (JSON)