Language-Driven Image Restoration and Semantic-Aware Quality Assessment: A Survey

Image restoration aims to recover a high-quality image from its degraded counterpart by mitigating distortions introduced during acquisition, transmission, or environmental interaction. Despite the remarkable progress of deep learning–based restoration models, most conventional approaches remain tightly coupled to predefined degradation assumptions and pixel-level supervision, limiting their capability to handle complex and diverse scenarios or user-dependent restoration targets. Recent advances in multimodal large language models (MLLMs) and vision–language models (VLMs) have introduced a new paradigm in which restoration systems incorporate semantic reasoning, language-driven interaction, and cross-modal knowledge. By integrating language models, restoration is extended beyond low-level reconstruction toward degradation interpretation, perceptual alignment, and high-level controllability. In this survey, we provide a systematic review of language-driven image restoration, organized through an interaction-centric taxonomy that characterizes how language models are coupled with restoration pipelines. We analyze representative frameworks from the perspectives of semantic conditioning, perceptual supervision, and execution-level interaction, and discuss how these mechanisms influence restoration objectives and system design. In addition, we review emerging language-driven image quality assessment (IQA) approaches, highlighting their complementary role to conventional fidelity-based metrics. Finally, we identify unresolved challenges and outline potential research directions toward more robust, efficient, and trustworthy restoration techniques. https://github.com/MingyuLiu1/Language-Driven-IR-and-IQA