Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration

2026-03-02

AI Summary

This work proposes DATPRL-IR, a unified cross-domain image restoration framework that addresses the challenge of simultaneously handling diverse tasks across multiple domains—such as natural images, medical imaging, and remote sensing—where existing all-in-one methods struggle to maintain performance. The method introduces task and domain prompt pools, combined with a prompt composition mechanism, to adaptively generate instance-level task and domain representations, which are fused into domain-aware task prompts. Furthermore, domain-specific prior knowledge is distilled from a multimodal large language model and injected into the domain prompts to enhance generalization. Extensive experiments demonstrate that DATPRL-IR significantly outperforms state-of-the-art approaches across various tasks and domains, achieving both high performance and strong generalization capability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Recently, significant breakthroughs have been made in all-in-one image restoration (AiOIR), which can handle multiple restoration tasks with a single model. However, existing methods typically focus on a specific image domain, such as natural scene, medical imaging, or remote sensing. In this work, we aim to extend AiOIR to multiple domains and propose the first multi-domain all-in-one image restoration method, DATPRL-IR, based on our proposed Domain-Aware Task Prompt Representation Learning. Specifically, we first construct a task prompt pool containing multiple task prompts, in which task-related knowledge is implicitly encoded. For each input image, the model adaptively selects the most relevant task prompts and composes them into an instance-level task representation via a prompt composition mechanism (PCM). Furthermore, to endow the model with domain awareness, we introduce another domain prompt pool and distill domain priors from multimodal large language models into the domain prompts. PCM is utilized to combine the adaptively selected domain prompts into a domain representation for each input image. Finally, the two representations are fused to form a domain-aware task prompt representation which can make full use of both specific and shared knowledge across tasks and domains to guide the subsequent restoration process. Extensive experiments demonstrate that our DATPRL-IR significantly outperforms existing SOTA image restoration methods, while exhibiting strong generalization capabilities. Code is available at https://github.com/GuangluDong0728/DATPRL-IR.

Problem

• multi-domain
• all-in-one image restoration
• domain-aware
• task prompt
• image restoration

Innovation

• Domain-Aware Prompt Learning
• Multi-Domain Image Restoration
• Task Prompt Representation
• Prompt Composition Mechanism
• All-in-One Restoration