mlsanityData to 7 Oct 2026

UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior

arXiv 2501.13134 ↗First posted 22 Jan 2025eess.IV cs.LGcited by 39

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Image restoration aims to recover content from inputs degraded by various factors, such as adverse weather, blur, and noise. Perceptual Image Restoration (PIR) methods improve visual quality but often do not support downstream tasks effectively. On the other hand, Task-oriented Image Restoration (TIR) methods focus on enhancing image utility for high-level vision tasks, sometimes compromising visual quality. This paper introduces UniRestore, a unified image restoration model that bridges the gap between PIR and TIR by using a diffusion prior. The diffusion prior is designed to generate images that align with human visual quality preferences, but these images are often unsuitable for TIR scenarios. To solve this limitation, UniRestore utilizes encoder features from an autoencoder to adapt the diffusion prior to specific tasks. We propose a Complementary Feature Restoration Module (CFRM) to reconstruct degraded encoder features and a Task Feature Adapter (TFA) module to facilitate adaptive feature fusion in the decoder. This design allows UniRestore to optimize images for both human perception and downstream task requirements, addressing discrepancies between visual quality and functional needs. Integrating these modules also enhances UniRestore's adapability and efficiency across diverse tasks. Extensive expertments demonstrate the superior performance of UniRestore in both PIR and TIR scenarios.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 59 of its 86 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

59 of 86 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model17 Mar
  2. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior29 Aug
  3. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model25 Aug
  4. 2023A Unified Conditional Framework for Diffusion-based Image Restoration31 May
  5. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  7. 2023DiffIR: Efficient Diffusion Model for Image Restoration16 Mar
  8. 2022Multiscale Structure Guided Diffusion for Image Deblurring4 Dec
  9. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models29 Jul
  10. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec
  11. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  12. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
36 more
  1. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  3. 2022Visual Prompt Tuningcited by 1,674
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2018Group Normalizationcited by 1,514
  7. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  8. 2021Multi-Stage Progressive Image Restorationcited by 813
  9. 2023Adversarial Diffusion Distillationcited by 741
  10. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  11. 2022Simple Baselines for Image Restorationcited by 701
  12. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  13. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  14. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  15. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  16. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  17. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  18. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  19. 2021Towards Robust Vision Transformercited by 137
  20. 2020A Model-driven Deep Neural Network for Single Image Rain Removalcited by 125
  21. 2021Image-Adaptive YOLO for Object Detection in Adverse Weather Conditionscited by 85
  22. 2022NAFSSR: Stereo Image Super-Resolution Using NAFNetcited by 75
  23. 2020Image Restoration for Under-Display Cameracited by 47
  24. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  25. 2023SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editingcited by 37
  26. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  27. 2018Light-Weight RefineNet for Real-Time Semantic Segmentationcited by 27
  28. 2020URIE: Universal Image Enhancement for Visual Recognition in the Wildcited by 27
  29. 2018Does Haze Removal Help CNN-based Image Classification?cited by 20
  30. 2020Exploring Image Enhancement for Salient Object Detection in Low Light Imagescited by 20
  31. 2023DiffuVolume: Diffusion Model for Volume based Stereo Matchingcited by 16
  32. 2017Classification Driven Dynamic Image Enhancementcited by 15
  33. 2023Counting Crowds in Bad Weathercited by 14
  34. 2024Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solutioncited by 14
  35. 2022RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learningcited by 5
  36. 2024AllWeatherNet:Unified Image Enhancement for Autonomous Driving under Adverse Weather and Lowlight-conditionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 27.

39 papers.

Sort:

By area:

  1. 2026Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restorationcited by 14
  2. 2025Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularizationcited by 8
  3. 2025Exploiting Diffusion Prior for Task-driven Image Restorationcited by 7
  4. 2025UniSER: A Foundation Model for Unified Soft Effects Removalcited by 5
  5. 2026LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Resultscited by 5
  6. 2025Universal Image Restoration Pre-training via Masked Degradation Classificationcited by 4
  7. 2025Towards Consistent and Controllable Image Synthesis for Face Editingcited by 3
  8. 2025Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentationcited by 3
  9. 2025FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restorationcited by 3
  10. 2026TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restorationcited by 3
  11. 2025Low-Bitrate Video Compression through Semantic-Conditioned Diffusioncited by 2
  12. 2026Restore, Assess, Repeat: A Unified Framework for Iterative Image Restorationcited by 2
27 more
  1. 2026NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weathercited by 2
  2. 2026TaskTok: Delving into Task Tokens for Task-driven Image Restorationcited by 2
  3. 2026PixRestore: Unified Image Restoration via Pixel Diffusion Transformercited by 2
  4. 2025DiffVQA: Video Quality Assessment Using Diffusion Feature Extractorcited by 1
  5. 2025Degradation-Aware All-in-One Image Restoration via Latent Prior Encodingcited by 1
  6. 2026Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipelinecited by 1
  7. 2026Task-Guided Prompting for Unified Remote Sensing Image Restorationcited by 1
  8. 2026Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Modelscited by 1
  9. 2026Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignmentcited by 1
  10. 2025Real-World Scene Recovery for Scattering-Degraded Images Using Spatial and Frequency Priorscited by 0
  11. 2025Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restorationcited by 0
  12. 2026Bridging Degradation Discrimination and Generation for Universal Image Restorationcited by 0
  13. 2026RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradationscited by 0
  14. 2026Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoisingcited by 0
  15. 2026When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noisecited by 0
  16. 2026EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learningcited by 0
  17. 2026CURE: Controllable Unified Image Restoration for Complex Degradationscited by 0
  18. 2026DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identificationcited by 0
  19. 2026Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priorscited by 0
  20. 2026What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restorationcited by 0
  21. 2026FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restorationcited by 0
  22. 2026Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generationcited by 0
  23. 2026SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restorationcited by 0
  24. 2026Weather-Conditioned Depth Anythingcited by 0
  25. 2026TaskGuard: Task-Conditioned Restoration Utility for Risk-Aware Object Detectioncited by 0
  26. 2026ImIR: Image-Instruction Tuning for All-in-One Image Restorationcited by 0
  27. 2026TaskIR: Task-Driven Image Restoration via Degradation Adaptation and Task Feedbackcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration
  2. 2026ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration
  3. 2024UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity
  4. 2025UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement
  5. 2025UniUIR: Considering Underwater Image Restoration as An All-in-One Learner
  6. 2025AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting
  7. 2024Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers
  8. 2025UniRes: Universal Image Restoration for Complex Degradations