Research map / Image generation / Image restoration
InstructIR: High-Quality Image Restoration Following Human Instructions
Marcos V. Conde, Gregor Geigle, Radu Timofte
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add human-written text instructions to NAFNet restoration (ablation) | InstructIR · 5-task average | PSNR: 27.84 -> 29.55 | Improved |
| add text instructions on GoPro deblurring (ablation) | InstructIR · GoPro | PSNR: 26.65 -> 29.40 | Improved |
| add text instructions in the 3-task setting (ablation) | InstructIR · 3D average | PSNR: 30.65 -> 32.43 | Improved |
| use ambiguous instead of precise instructions (ablation) | InstructIR-5D · LOL | PSNR: 23.00 -> 21.85 | Hurt |
| use ambiguous instead of precise instructions (ablation) | InstructIR-5D · Rain100L | PSNR: 36.84 -> 36.24 | Hurt |
| swap text encoder BGE-micro for all-MiniLM or CLIP (ablation) | InstructIR-5D · LOL | PSNR: 23.00 -> 22.98 (MiniLM), 22.95 (CLIP) | No clear effect |
| add super-resolution as sixth training task (ablation) | InstructIR-5D · GoPro | PSNR: 29.40 -> 29.73 | Improved |
| add MIT5K enhancement as seventh task (ablation) | InstructIR-6D · Rain100L | PSNR: 36.80 -> 36.75 | No clear effect |
| train on 5 tasks instead of 3 tasks (ablation) | InstructIR · Rain100L | PSNR: 37.98 -> 36.84 | Hurt |
| use InstructIR with 16M parameters instead of PromptIR | all-in-one restoration · Inference cost | MACs (G): 160 -> 100 | Improved |
Later papers that compared with this method
8 later accepted papers report InstructIR as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration (ICML 2026 · better on 2 of 2 shared results)
- UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration (CVPR 2026 · better on 1 of 1 shared result)
- ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration (AAAI 2026 · better on 0 of 1 shared result)
- Degradation-Aware Feature Perturbation for All-in-One Image Restoration (CVPR 2025 · better on 7 of 12 shared results)
- PixTalk: Controlling Photorealistic Image Processing and Editing with Language (ICCV 2025 · better on 1 of 2 shared results)
- Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration (TPAMI 2025 · better on 2 of 2 shared results)
- MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration (ICCV 2025 · better on 1 of 1 shared result)
- RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models (NeurIPS 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- InstructRestore: Region-Customized Image Restoration with Human Instructions (NeurIPS 2025 · similarity 0.91)
- Improving Image Restoration through Removing Degradations in Textual Representations (CVPR 2024 · similarity 0.89)
- Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration (CVPR 2025 · similarity 0.88)
- Intra and Inter Parser-Prompted Transformers for Effective Image Restoration (AAAI 2025 · similarity 0.87)
- Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild (CVPR 2024 · similarity 0.87)
- UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement (CVPR 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
