Prompt-based Ingredient-Oriented All-in-One Image Restoration
This addresses the need for versatile image restoration models in real-world applications where multiple degradation types occur, though it appears incremental as it builds on existing prompt-based and hybrid CNN-Transformer architectures.
The paper tackles the problem of single models being unable to handle multiple image degradation types by proposing CAPTNet, a prompt-based approach that uses degradation-specific prompts to guide a single model in restoring images affected by various degradations, achieving competitive performance with state-of-the-art methods.
Image restoration aims to recover the high-quality images from their degraded observations. Since most existing methods have been dedicated into single degradation removal, they may not yield optimal results on other types of degradations, which do not satisfy the applications in real world scenarios. In this paper, we propose a novel data ingredient-oriented approach that leverages prompt-based learning to enable a single model to efficiently tackle multiple image degradation tasks. Specifically, we utilize a encoder to capture features and introduce prompts with degradation-specific information to guide the decoder in adaptively recovering images affected by various degradations. In order to model the local invariant properties and non-local information for high-quality image restoration, we combined CNNs operations and Transformers. Simultaneously, we made several key designs in the Transformer blocks (multi-head rearranged attention with prompts and simple-gate feed-forward network) to reduce computational requirements and selectively determines what information should be persevered to facilitate efficient recovery of potentially sharp images. Furthermore, we incorporate a feature fusion mechanism further explores the multi-scale information to improve the aggregated features. The resulting tightly interlinked hierarchy architecture, named as CAPTNet, extensive experiments demonstrate that our method performs competitively to the state-of-the-art.