Distilling Semantic Priors from SAM to Efficient Image Restoration Models

TL;DR

This paper introduces a framework to distill semantic priors from the powerful SAM model into existing image restoration models, significantly improving their performance without increasing inference costs.

Contribution

The proposed framework effectively transfers semantic knowledge from SAM to IR models through fusion and self-distillation, enhancing IR performance efficiently.

Findings

Improved IR model performance across deraining, deblurring, and denoising tasks.

Framework reduces computational costs by avoiding direct SAM inference during IR.

Semantic priors distillation enhances the semantic understanding of IR models.

Abstract

In image restoration (IR), leveraging semantic priors from segmentation models has been a common approach to improve performance. The recent segment anything model (SAM) has emerged as a powerful tool for extracting advanced semantic priors to enhance IR tasks. However, the computational cost of SAM is prohibitive for IR, compared to existing smaller IR models. The incorporation of SAM for extracting semantic priors considerably hampers the model inference efficiency. To address this issue, we propose a general framework to distill SAM's semantic knowledge to boost exiting IR models without interfering with their inference process. Specifically, our proposed framework consists of the semantic priors fusion (SPF) scheme and the semantic priors distillation (SPD) scheme. SPF fuses two kinds of information between the restored image predicted by the original IR model and the semantic mask predicted by SAM for the refined restored image. SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models. Additionally, we design a semantic-guided relation (SGR) module for SPD, which ensures semantic feature representation space consistency to fully distill the priors. We demonstrate the effectiveness of our framework across multiple IR models and tasks, including deraining, deblurring, and denoising.