mlsanityData to 7 Oct 2026

The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

arXiv 2607.21118 ↗First posted 23 Jul 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common benchmark for evaluating the restoration accuracy, robustness, and generalization capability of models across multiple degradation categories within a unified framework. The competition attracted 158 registered participants, and 20 teams were included in the final ranking after their submitted results were successfully reproduced and verified. This report provides a comprehensive analysis of the submitted solutions and corresponding results, highlighting recent advances in real-world all-in-one image restoration. The summarized methods and empirical findings reveal effective design strategies and establish an updated benchmark for future research in real-world low-level vision.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 41 of its 50 references that are in the map. First posted on arXiv 23 Jul 2026.

Builds on

41 of 50 references.

References · 41

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2019Searching for MobileNetV3cited by 1,984
  7. 2020GLU Variants Improve Transformercited by 1,724
  8. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  9. 2019Root Mean Square Layer Normalizationcited by 1,425
  10. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,311
  11. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  12. 2022Simple Baselines for Image Restorationcited by 701
29 more
  1. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  2. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  3. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 204
  4. 2020Human-Aware Motion Deblurringcited by 174
  5. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 164
  6. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 113
  7. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  8. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  9. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 62
  10. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  11. 2023A Comparative Study of Image Restoration Networks for General Backbone Network Designcited by 56
  12. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
  13. 2024FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restorationcited by 37
  14. 2026HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformercited by 29
  15. 2024Efficient Visual State Space Model for Image Deblurringcited by 27
  16. 2025NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 22
  17. 2024PromptCIR: Blind Compressed Image Restoration with Prompt Learningcited by 20
  18. 2025WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restorationcited by 20
  19. 2025FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Modelcited by 9
  20. 2025Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularizationcited by 8
  21. 2026Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restorationcited by 6
  22. 2025Rethinking Nighttime Image Deraining via Learnable Color Space Transformationcited by 5
  23. 2026LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Resultscited by 5
  24. 2025Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuningcited by 4
  25. 2025DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Modelcited by 3
  26. 2025SmokeBench: A Real-World Dataset for Surveillance Image Desmoking in Early-Stage Fire Scenescited by 3
  27. 2026UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimizationcited by 2
  28. 2026X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challengecited by 2
  29. 2025Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theorycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Resultscited by 0