mlsanityData to 7 Oct 2026

Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey

arXiv 2404.16484 ↗First posted 25 Apr 2024cs.CV eess.IVcited by 19

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing a variety of 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 10ms. Out of the 160 participants, 25 teams submitted their code and models. The solutions present novel designs tailored for memory-efficiency and runtime on edge devices. This survey describes the best solutions for real-time SR of compressed high-resolution images.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 25 Apr 2024.

Builds on

33 of 45 references.

References · 33

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  3. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  4. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  6. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  7. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  8. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  9. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 204
  10. 2017Playing for Benchmarkscited by 169
  11. 2017Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networkscited by 138
  12. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
21 more
  1. 2020Residual Feature Distillation Network for Lightweight Image Super-Resolutioncited by 122
  2. 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
  3. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 114
  4. 2020Efficient Image Super-Resolution Using Pixel Attentioncited by 87
  5. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
  6. 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 56
  7. 2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
  8. 2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
  9. 2019Efficient Residual Dense Block Search for Image Super-Resolutioncited by 37
  10. 2020AIM 2020 Challenge on Efficient Super-Resolution: Methods and Resultscited by 36
  11. 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
  12. 2022Fast and Memory-Efficient Network Towards Efficient Image Super-Resolutioncited by 27
  13. 2023Swift Parameter-free Attention Network for Efficient Super-Resolutioncited by 24
  14. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  15. 2023DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolutioncited by 19
  16. 2024Event-Based Eye Tracking. AIS 2024 Challenge Surveycited by 19
  17. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
  18. 2020It Is Likely That Your Loss Should be a Likelihoodcited by 5
  19. 2021ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Imagescited by 5
  20. 2024AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Resultscited by 4
  21. 2022Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolutioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 7; 2026: 6.

19 papers.

Sort:

By area:

  1. 2024Towards Realistic Data Generation for Real-World Super-Resolutioncited by 56
  2. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  3. 2024S3Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Modelcited by 12
  4. 2024AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Contentcited by 7
  5. 2026Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separationcited by 5
  6. 2025Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignmentcited by 4
  7. 2024Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Resultscited by 3
  8. 2025SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolutioncited by 2
  9. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 2
  10. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarkingcited by 2
  11. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offscited by 1
  12. 2024Sebica: Lightweight Spatial and Efficient Bidirectional Channel Attention Super Resolution Networkcited by 0
7 more
  1. 2025Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Contentcited by 0
  2. 2025Per-channel autoregressive linear prediction padding in tiled CNN processing of 2D spatial datacited by 0
  3. 2025SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Imagescited by 0
  4. 2025DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Derainingcited by 0
  5. 2026When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editingcited by 0
  6. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarkingcited by 0
  7. 2026ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysiscited by 0