Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918441692168192 |
|---|---|
| author | Zhou, Yingjie Cao, Jiezhang Wen, Farong Zhang, Zicheng Zhou, Yu Shi, Yue Liu, Xiaohong Timofte, Radu Van Gool, Luc Zhai, Guangtao |
| author_facet | Zhou, Yingjie Cao, Jiezhang Wen, Farong Zhang, Zicheng Zhou, Yu Shi, Yue Liu, Xiaohong Timofte, Radu Van Gool, Luc Zhai, Guangtao |
| contents | Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Training specific models for specific degradation may lead to poor generalization. To handle multiple degradations simultaneously, All-in-One models might sacrifice performance on certain types of degradation and still struggle with unseen degradations during training. Existing IR agents rely on multimodal large language models (MLLM) and a time-consuming rolling-back selection strategy neglecting image quality. As a result, they may misinterpret degradations and have high time and computational costs to conduct unnecessary IR tasks with redundant order. To address these, we propose a Quality-Driven agent (Q-Agent) via Chain-of-Thought (CoT) restoration. Specifically, our Q-Agent consists of robust degradation perception and quality-driven greedy restoration. The former module first fine-tunes MLLM, and uses CoT to decompose multi-degradation perception into single-degradation perception tasks to enhance the perception of MLLMs. The latter employs objective image quality assessment (IQA) metrics to determine the optimal restoration sequence and execute the corresponding restoration algorithms. Experimental results demonstrate that our Q-Agent achieves superior IR performance compared to existing All-in-One models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07148 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model Zhou, Yingjie Cao, Jiezhang Wen, Farong Zhang, Zicheng Zhou, Yu Shi, Yue Liu, Xiaohong Timofte, Radu Van Gool, Luc Zhai, Guangtao Image and Video Processing Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Training specific models for specific degradation may lead to poor generalization. To handle multiple degradations simultaneously, All-in-One models might sacrifice performance on certain types of degradation and still struggle with unseen degradations during training. Existing IR agents rely on multimodal large language models (MLLM) and a time-consuming rolling-back selection strategy neglecting image quality. As a result, they may misinterpret degradations and have high time and computational costs to conduct unnecessary IR tasks with redundant order. To address these, we propose a Quality-Driven agent (Q-Agent) via Chain-of-Thought (CoT) restoration. Specifically, our Q-Agent consists of robust degradation perception and quality-driven greedy restoration. The former module first fine-tunes MLLM, and uses CoT to decompose multi-degradation perception into single-degradation perception tasks to enhance the perception of MLLMs. The latter employs objective image quality assessment (IQA) metrics to determine the optimal restoration sequence and execute the corresponding restoration algorithms. Experimental results demonstrate that our Q-Agent achieves superior IR performance compared to existing All-in-One models. |
| title | Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2504.07148 |