Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration
This work addresses the problem of adaptive and generalizable image restoration for computer vision applications, representing an incremental advancement through novel integration of multimodal prompts.
The paper tackled the challenge of handling diverse real-world degradations in all-in-one image restoration by introducing MPerceiver, a multimodal prompt learning approach that leverages Stable Diffusion priors, achieving state-of-the-art performance across 9 training tasks and demonstrating strong zero-shot and few-shot capabilities on 16 tasks.
Despite substantial progress, all-in-one image restoration (IR) grapples with persistent challenges in handling intricate real-world degradations. This paper introduces MPerceiver: a novel multimodal prompt learning approach that harnesses Stable Diffusion (SD) priors to enhance adaptiveness, generalizability and fidelity for all-in-one image restoration. Specifically, we develop a dual-branch module to master two types of SD prompts: textual for holistic representation and visual for multiscale detail representation. Both prompts are dynamically adjusted by degradation predictions from the CLIP image encoder, enabling adaptive responses to diverse unknown degradations. Moreover, a plug-in detail refinement module improves restoration fidelity via direct encoder-to-decoder information transformation. To assess our method, MPerceiver is trained on 9 tasks for all-in-one IR and outperforms state-of-the-art task-specific methods across most tasks. Post multitask pre-training, MPerceiver attains a generalized representation in low-level vision, exhibiting remarkable zero-shot and few-shot capabilities in unseen tasks. Extensive experiments on 16 IR tasks underscore the superiority of MPerceiver in terms of adaptiveness, generalizability and fidelity.