Domain-adaptive Video Deblurring via Test-time Blurring

TL;DR

This paper introduces a domain adaptation method for video deblurring that uses test-time fine-tuning with generated training pairs, significantly improving performance on real-world videos without requiring paired data.

Contribution

It proposes a novel test-time domain adaptation scheme utilizing a blurring model and pseudo-sharp images to calibrate deblurring models for unseen real-world domains.

Findings

Achieves up to 7.54dB performance gain on real-world datasets.

Effectively adapts deblurring models to unseen domains without paired training data.

Demonstrates significant improvement over state-of-the-art methods.

Abstract

Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due to the domain gap between training and testing videos, especially for those captured in real-world scenarios. To address this issue, we propose a domain adaptation scheme based on a blurring model to achieve test-time fine-tuning for deblurring models in unseen domains. Since blurred and sharp pairs are unavailable for fine-tuning during inference, our scheme can generate domain-adaptive training pairs to calibrate a deblurring model for the target domain. First, a Relative Sharpness Detection Module is proposed to identify relatively sharp regions from the blurry input images and regard them as pseudo-sharp images. Next, we utilize a blurring model to produce blurred images based on the pseudo-sharp images extracted during testing. To synthesize blurred images in compliance with the target data distribution, we propose a Domain-adaptive Blur Condition Generation Module to create domain-specific blur conditions for the blurring model. Finally, the generated pseudo-sharp and blurred pairs are used to fine-tune a deblurring model for better performance. Extensive experimental results demonstrate that our approach can significantly improve state-of-the-art video deblurring methods, providing performance gains of up to 7.54dB on various real-world video deblurring datasets. The source code is available at https://github.com/Jin-Ting-He/DADeblur.