Dynamic Scene Deblurring Based on Continuous Cross-Layer Attention Transmission

Hua, Xia; Li, Mingxin; Fei, Junxiong; Liu, Jianguo; Hong, Hanyu

doi:10.2139/ssrn.4347112

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the proposed deblurring network with the stateof-the-art restoration models, including MIMO-UNet [7], MIRNet-v2 [28], NAFNet [36], XYDeblur [40], Sim-pleNet [41], RDAFNet [42], Stripformer [12], Uformer-B [11], Restormer [10], and FFTformer [27].…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Real‐world image deblurring using data synthesis and feature complementary network

Wei,

Ge,

Qiao

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Many learning‐based approaches to image deblurring have received increasing attention in recent years. However, the models trained on existing synthetic datasets do not generalize well to real‐world blur, resulting in undesirable artifacts and residual blur. This work attempts to address this problem from two aspects: training data synthesis and network architecture. To narrow the domain gap between synthetic and real domains, a realistic blur synthesis pipeline to generate high‐quality blurred data is proposed. Since the blur is non‐uniform and has different scales and degrees, a parallel feature complementary module to fully exploit the local and non‐local information, which improves the feature representation and helps the network to perceive the non‐uniform blur, is developed. In addition, a spatial Fourier reconstruction block to facilitate correct detail recovery in the spatial and Fourier domains is introduced. Based on these two designs, an effective encoder–decoder network for deblurring is designed. Extensive experiments demonstrate the validity and superiority of the proposed blur synthesis method and deblurring network. In particular, the proposed deblurring network can achieve superior or comparable performance to Restormer, while saving 70% of network parameters and 53% of floating point operations (FLOPs).

show abstract