期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 32, 期 -, 页码 1390-1402出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2023.3244417
关键词
Image restoration; Deconvolution; Kernel; Training; Photography; Convergence; Photonics; Non-blind deblurring; low-light; image and feature space; deep wiener deconvolution
This article presents a novel non-blind deblurring method called INFWIDE, which can effectively tackle the challenges in low-light photography. By employing a two-branch architecture and fusion network, INFWIDE is able to remove noise, hallucinate saturated regions, and achieve high quality night photograph deblurring. The proposed approach demonstrates superior performance in both synthetic and real data experiments.
Under low-light environment, handheld photography suffers from severe camera shake under long exposure settings. Although existing deblurring algorithms have shown promising performance on well-exposed blurry images, they still cannot cope with low-light snapshots. Sophisticated noise and saturation regions are two dominating challenges in practical low-light deblurring: the former violates the Gaussian or Poisson assumption widely used in most existing algorithms and thus degrades their performance badly, while the latter introduces non-linearity to the classical convolution-based blurring model and makes the deblurring task even challenging. In this work, we propose a novel non-blind deblurring method dubbed image and feature space Wiener deconvolution network (INFWIDE) to tackle these problems systematically. In terms of algorithm design, INFWIDE proposes a two-branch architecture, which explicitly removes noise and hallucinates saturated regions in the image space and suppresses ringing artifacts in the feature space, and integrates the two complementary outputs with a subtle multi-scale fusion network for high quality night photograph deblurring. For effective network training, we design a set of loss functions integrating a forward imaging model and backward reconstruction to form a close-loop regularization to secure good convergence of the deep neural network. Further, to optimize INFWIDE's applicability in real low-light conditions, a physical-process-based low-light noise model is employed to synthesize realistic noisy night photographs for model training. Taking advantage of the traditional Wiener deconvolution algorithm's physically driven characteristics and deep neural network's representation ability, INFWIDE can recover fine details while suppressing the unpleasant artifacts during deblurring. Extensive experiments on synthetic data and real data demonstrate the superior performance of the proposed approach.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据