Rethinking Blur Synthesis for Deep Real-World Image Deblurring
It addresses the problem of domain shift in deblurring models for real-world applications, offering incremental improvements in training data synthesis and network design.
The paper tackles real-world image deblurring by proposing a realistic blur synthesis pipeline to reduce domain shift and a multi-path transformer module in a UNet architecture, achieving better performance than state-of-the-art methods on three real-world datasets.
In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design. Deblurring models trained on existing synthetic datasets perform poorly on real blurry images due to domain shift. To reduce the domain gap between synthetic and real domains, we propose a novel realistic blur synthesis pipeline to simulate the camera imaging process. As a result of our proposed synthesis method, existing deblurring models could be made more robust to handle real-world blur. Furthermore, we develop an effective deblurring model that captures non-local dependencies and local context in the feature domain simultaneously. Specifically, we introduce the multi-path transformer module to UNet architecture for enriched multi-scale features learning. A comprehensive experiment on three real-world datasets shows that the proposed deblurring model performs better than state-of-the-art methods.