mlsanityData to 14 Oct 2026

Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report

arXiv 2510.12788 ↗First posted 14 Oct 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper reviews the AIM 2025 Efficient Real-World Deblurring using Single Images Challenge, which aims to advance in efficient real-blur restoration. The challenge is based on a new test set based on the well known RSBlur dataset. Pairs of blur and degraded images in this dataset are captured using a double-camera system. Participant were tasked with developing solutions to effectively deblur these type of images while fulfilling strict efficiency constraints: fewer than 5 million model parameters and a computational budget under 200 GMACs. A total of 71 participants registered, with 4 teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 31.1298 dB, showcasing the potential of efficient methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers in efficient real-world image deblurring.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

22 of 41 references.

References · 22

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  2. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  3. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  4. 2022Simple Baselines for Image Restorationcited by 708
  5. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  6. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  7. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 165
  8. 2022Stripformer: Strip Transformer for Fast Image Deblurringcited by 140
  9. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  10. 2022Realistic Blur Synthesis for Learning Image Deblurringcited by 53
  11. 2021NTIRE 2021 Challenge on Image Deblurringcited by 50
  12. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
10 more
  1. 2021BANet: Blur-aware Attention Networks for Dynamic Scene Deblurringcited by 45
  2. 2021Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Networkcited by 26
  3. 2025The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Reportcited by 26
  4. 2022Real-World Deep Local Motion Deblurringcited by 21
  5. 2023GELU Activation Function in Deep Learning: A Comprehensive Mathematical Analysis and Performancecited by 16
  6. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  7. 2025AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Resultscited by 14
  8. 2020NTIRE 2020 Challenge on Image and Video Deblurringcited by 11
  9. 2025AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Resultscited by 8
  10. 2025AIM 2025 Rip Current Segmentation (RipSeg) Challenge Reportcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Resultscited by 11
  2. 2026FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurringcited by 0