# Frequency-oriented hierarchical fusion network for single image raindrop removal

## TL;DR

This paper introduces a new method for removing raindrops from images by focusing on frequency information to improve image quality and reduce artifacts.

## Contribution

The paper proposes a frequency-oriented Hierarchical Fusion Network with a dynamic adaptive frequency loss and calibrated attention mechanism.

## Key findings

- The proposed method outperforms existing methods in raindrop removal.
- The dynamic adaptive frequency loss helps recover high-frequency components effectively.
- The hierarchical fusion network improves contextual and spatial feature learning.

## Abstract

Single image raindrop removal aims at recovering high-resolution images from degraded ones. However, existing methods primarily employ pixel-level supervision between image pairs to learn spatial features, thus ignoring the more discriminative frequency information. This drawback results in the loss of high-frequency structures and the generation of diverse artifacts in the restored image. To ameliorate this deficiency, we propose a novel frequency-oriented Hierarchical Fusion Network (HFNet) for raindrop image restoration. Specifically, to compensate for spatial representation deficiencies, we design a dynamic adaptive frequency loss (DAFL), which allows the model to adaptively handle the high-frequency components that are difficult to recover. To handle spatially diverse raindrops, we propose a hierarchical fusion network to efficiently learn both contextual information and spatial features. Meanwhile, a calibrated attention mechanism is proposed to facilitate the transfer of valuable information. Comparative experiments with existing methods indicate the advantages of the proposed algorithm.