Let Segment Anything Help Image Dehaze

TL;DR

This paper introduces a framework that leverages large-model prior knowledge to enhance low-level image dehazing tasks, improving performance without additional data or training resources.

Contribution

It proposes a novel method to integrate large-model priors into low-level vision tasks like dehazing, addressing overfitting and local optima issues in small datasets.

Findings

Large-model prior integration improves dehazing performance.

The framework reduces training time and resource requirements.

Ablation studies confirm the effectiveness of proposed modules.

Abstract

The large language model and high-level vision model have achieved impressive performance improvements with large datasets and model sizes. However, low-level computer vision tasks, such as image dehaze and blur removal, still rely on a small number of datasets and small-sized models, which generally leads to overfitting and local optima. Therefore, we propose a framework to integrate large-model prior into low-level computer vision tasks. Just as with the task of image segmentation, the degradation of haze is also texture-related. So we propose to detect gray-scale coding, network channel expansion, and pre-dehaze structures to integrate large-model prior knowledge into any low-level dehazing network. We demonstrate the effectiveness and applicability of large models in guiding low-level visual tasks through different datasets and algorithms comparison experiments. Finally, we demonstrate the effect of grayscale coding, network channel expansion, and recurrent network structures through ablation experiments. Under the conditions where additional data and training resources are not required, we successfully prove that the integration of large-model prior knowledge will improve the dehaze performance and save training time for low-level visual tasks.