Vision-Language Model Guided Image Restoration

TL;DR

This paper introduces VLMIR, a novel image restoration framework that leverages vision-language models like CLIP to incorporate semantic priors, resulting in improved visual perception and semantic coherence in restored images.

Contribution

The paper proposes a two-stage VLMIR framework that integrates vision-language priors into diffusion-based image restoration, enhancing both pixel fidelity and semantic understanding.

Findings

VLMIR outperforms existing methods on multiple IR benchmarks.

Incorporating linguistic priors improves semantic coherence in restored images.

Ablation studies confirm the effectiveness of VLM-based feature extraction.

Abstract

Many image restoration (IR) tasks require both pixel-level fidelity and high-level semantic understanding to recover realistic photos with fine-grained details. However, previous approaches often struggle to effectively leverage both the visual and linguistic knowledge. Recent efforts have attempted to incorporate Vision-language models (VLMs), which excel at aligning visual and textual features, into universal IR. Nevertheless, these methods fail to utilize the linguistic priors to ensure semantic coherence during the restoration process. To address this issue, in this paper, we propose the Vision-Language Model Guided Image Restoration (VLMIR) framework, which leverages the rich vision-language priors of VLMs, such as CLIP, to enhance IR performance through improved visual perception and semantic understanding. Our approach consists of two stages: VLM-based feature extraction and diffusion-based image restoration. In the first stage, we extract complementary visual and linguistic representations of input images by condensing the visual perception and high-level semantic priors through VLMs. Specifically, we align the embeddings of captions from low-quality and high-quality images using a cosine similarity loss with LoRA fine-tuning, and employ a degradation predictor to decompose degradation and clean image content embeddings. These complementary visual and textual embeddings are then integrated into a diffusion-based model via cross-attention mechanisms for enhanced restoration. Extensive experiments and ablation studies demonstrate that VLMIR achieves superior performance across both universal and degradation-specific IR tasks, underscoring the critical role of integrated visual and linguistic knowledge from VLMs in advancing image restoration capabilities.