mlsanityData to 14 Oct 2026

Meta-Transfer Learning for Zero-Shot Super-Resolution

arXiv 2002.12213 ↗First posted 27 Feb 2020cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image. Another problem is that they are applicable only to the specific condition of data that they are supervised. For instance, the low-resolution (LR) image should be a "bicubic" downsampled noise-free image from a high-resolution (HR) one. To address both issues, zero-shot super-resolution (ZSSR) has been proposed for flexible internal learning. However, they require thousands of gradient updates, i.e., long inference time. In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR. Precisely, it is based on finding a generic initial parameter that is suitable for internal learning. Thus, we can exploit both external and internal information, where one single gradient update can yield quite considerable results. (See Figure 1). With our method, the network can quickly adapt to a given image condition. In this respect, our method can be applied to a large spectrum of image conditions within a fast adaptation process.

Key facts. Cited by 116 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 36; 2022: 33; 2023: 22; 2024: 13; 2025: 9; 2026: 3.

116 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  2. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  3. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 153
  4. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  5. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  6. 2021A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inversecited by 53
  7. 2021Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutioncited by 52
  8. 2022Deep Constrained Least Squares for Blind Image Super-Resolutioncited by 47
  9. 2021Deep Learning for HDR Imaging: State-of-the-Art and Future Trendscited by 45
  10. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 42
  11. 2021Blind Image Super-Resolution via Contrastive Representation Learningcited by 32
  12. 2022Knowledge Distillation based Degradation Estimation for Blind Super-Resolutioncited by 28
38 more
  1. 2022Variational Deep Image Restorationcited by 24
  2. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  3. 2022A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Boundscited by 22
  4. 2022PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularizationcited by 22
  5. 2022Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advancescited by 22
  6. 2022Basic Binary Convolution Unit for Binarized Image Restoration Networkcited by 22
  7. 2021A Two-Stage Attentive Network for Single Image Super-Resolutioncited by 20
  8. 2022Local Stochastic Bilevel Optimization with Momentum-Based Variance Reductioncited by 20
  9. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  10. 2024Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learningcited by 19
  11. 2023Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstructioncited by 18
  12. 2021End-to-end Alternating Optimization for Blind Super Resolutioncited by 17
  13. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  14. 2021Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learningcited by 17
  15. 2023Learning Distortion Invariant Representation for Image Restoration from A Causality Perspectivecited by 17
  16. 2022Adaptive Patch Exiting for Scalable Single Image Super-Resolutioncited by 16
  17. 2021Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulationcited by 15
  18. 2022Self-Supervised Deep Blind Video Super-Resolutioncited by 15
  19. 2023Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolutioncited by 14
  20. 2021Real-World Super-Resolution of Face-Images from Surveillance Camerascited by 11
  21. 2022Bayesian Image Super-Resolution with Deep Modeling of Image Statisticscited by 11
  22. 2022Meta-Learning based Degradation Representation for Blind Super-Resolutioncited by 11
  23. 2023Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learningcited by 10
  24. 2021MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworkscited by 9
  25. 2021Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directionscited by 9
  26. 2023Deep Internal Learning: Deep Learning from a Single Inputcited by 9
  27. 2021Attribute-Modulated Generative Meta Learning for Zero-Shot Classificationcited by 8
  28. 2022Efficient Meta-Tuning for Content-aware Neural Video Deliverycited by 8
  29. 2022RZSR: Reference-based Zero-Shot Super-Resolution with Depth Guided Self-Exemplarscited by 8
  30. 2022Joint Learning Content and Degradation Aware Feature for Blind Super-Resolutioncited by 8
  31. 2023End-to-end Alternating Optimization for Real-World Blind Super Resolutioncited by 8
  32. 2024CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolutioncited by 8
  33. 2024HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Priorcited by 8
  34. 2021Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradationscited by 7
  35. 2021Data Acquisition and Preparation for Dual-reference Deep Learning of Image Super-Resolutioncited by 7
  36. 2022Task-Adaptive Meta-Learning Framework for Advancing Spatial Generalizabilitycited by 7
  37. 2023Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Imagescited by 7
  38. 2023Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolutioncited by 7

50 most cited of 116 All 116 (JSON)