# Universal Image Restoration via Internalized Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2606.17557 · HTML: https://mlsanity.com/paper/2606.17557/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 60 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Thinking with Generated Images](https://mlsanity.com/paper/2505.22525/) (2025)
- [Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy](https://mlsanity.com/paper/2401.03379/) (2024)
- [Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model](https://mlsanity.com/paper/2504.07148/) (2025)
- [Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision](https://mlsanity.com/paper/2504.04903/) (2025)
- [Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers](https://mlsanity.com/paper/2410.08688/) (2024)
- [Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception](https://mlsanity.com/paper/2602.19596/) (2026)
- [Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations](https://mlsanity.com/paper/2604.24661/) (2026)

## Abstract (arXiv)

Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are common, their performance declines as degradation complexity increases. Recent works adopt Chain-of-Thought (CoT) reasoning for multi-round restoration using specialized modules. However, this approach faces two key limitations: (i) increased computational cost due to multi-step processing, and (ii) weak modeling of interactions between degradations during stepwise inference. We introduce CoTIR, a universal image restoration framework that internalizes CoT reasoning within a single model. Concretely, we view image restoration as a specialized subtask of image editing, which implies that a large-scale pre-trained editing model provides a more favorable optimization starting point. Building on this, we fine-tune the model for restoration and further encode structured CoT-style reasoning into the learning objective via a differentiable formulation inspired by Lagrangian optimization, enabling holistic restoration without chaining specialized restorers. To facilitate training and evaluation, we further present CoTIR-Bench, a large-scale benchmark comprising 5.2 million samples with CoT-style reasoning traces. Extensive experiments on CoTIR-Bench and broad real composite degradation scenes show that CoTIR achieves stronger perceptual quality and more competitive fidelity than both all-in-one models and multi-round restoration methods. The source code is available at https://github.com/gy65896/CoTIR.