Data to 7 Oct 2026

Single Image Super-Resolution via a Holistic Attention Network

arXiv 2008.08767 ↗First posted 20 Aug 2020eess.IV cs.CVcited by 265

Not on the map. Why?

Abstract (arXiv)

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.

Key facts. Cited by 265 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 75; 2023: 53; 2024: 59; 2025: 26; 2026: 20.

265 papers.

Sort:

By area:

2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
2021Transformers in Vision: A Surveycited by 1,009
2022Activating More Pixels in Image Super-Resolution Transformercited by 433
2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
2022Cross Aggregation Transformer for Image Restorationcited by 92
2024VmambaIR: Visual State Space Model for Image Restorationcited by 90

38 more

2022Accurate Image Restoration with Attention Retractable Transformercited by 85
2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 79
2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
2022NAFSSR: Stereo Image Super-Resolution Using NAFNetcited by 75
2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
2022SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolutioncited by 67
2021On Efficient Transformer-Based Image Pre-training for Low-Level Visioncited by 64
2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
2024Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionarycited by 63
2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 56
2023A Comparative Study of Image Restoration Networks for General Backbone Network Designcited by 56
2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
2021Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutioncited by 52
2021AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsamplingcited by 47
2024Frequency-Assisted Mamba for Remote Sensing Image Super-Resolutioncited by 47
2022N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolutioncited by 46
2023Neural Degradation Representation Learning for All-In-One Image Restorationcited by 46
2024MaIR: A Locality- and Continuity-Preserving Mamba for Image Restorationcited by 43
2024HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolutioncited by 42
2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
2024NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 40
2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
2022Revisiting RCAN: Improved Training for Image Super-Resolutioncited by 32
2021Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devicescited by 30
2021A Practical Contrastive Learning Framework for Single-Image Super-Resolutioncited by 30
2022Neural Data-Dependent Transform for Learned Image Compressioncited by 29
2022Multi-scale Attention Network for Single Image Super-Resolutioncited by 29
2023Recursive Generalization Transformer for Image Super-Resolutioncited by 28
2022Fast and Memory-Efficient Network Towards Efficient Image Super-Resolutioncited by 27
2022Self-supervised Character-to-Character Distillation for Text Recognitioncited by 27
2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restorationcited by 27
2021SRWarp: Generalized Image Super-Resolution under Arbitrary Transformationcited by 26
2021COMISR: Compression-Informed Video Super-Resolutioncited by 26
2023OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformercited by 26
2025Progressive Focused Transformer for Single Image Super-Resolutioncited by 25

50 most cited of 265 All 265 (JSON)