Unsupervised Raindrop Removal from a Single Image using Conditional Diffusion Models

TL;DR

This paper presents a novel unsupervised method for removing raindrops from a single image by leveraging conditional diffusion models, advancing the state-of-the-art in image inpainting without requiring paired training data.

Contribution

It introduces a diffusion-based image inpainting approach specifically designed for raindrop removal, bypassing the need for raindrop detection and paired datasets.

Findings

Effective raindrop removal demonstrated on single images

Outperforms traditional GAN-based methods in quality

Unsupervised approach reduces data annotation requirements

Abstract

Raindrop removal is a challenging task in image processing. Removing raindrops while relying solely on a single image further increases the difficulty of the task. Common approaches include the detection of raindrop regions in the image, followed by performing a background restoration process conditioned on those regions. While various methods can be applied for the detection step, the most common architecture used for background restoration is the Generative Adversarial Network (GAN). Recent advances in the use of diffusion models have led to state-of-the-art image inpainting techniques. In this paper, we introduce a novel technique for raindrop removal from a single image using diffusion-based image inpainting.