可解释性
计算机科学
梯度下降
人工智能
图像(数学)
图像复原
人工神经网络
深层神经网络
概化理论
深度学习
图像处理
数学
统计
作者
Chong Mou,Qian Wang,Jian Zhang
标识
DOI:10.1109/cvpr52688.2022.01688
摘要
Deep neural networks (DNN) have achieved great suc-cess in image restoration. However, most DNN methods are designed as a black box, lacking transparency and inter-pretability. Although some methods are proposed to combine traditional optimization algorithms with DNN, they usually demand pre-defined degradation processes or hand-crafted assumptions, making it difficult to deal with complex and real-world applications. In this paper, we propose a Deep Generalized Unfolding Network (DGUNet) for image restoration. Concretely, without loss of interpretability, we integrate a gradient estimation strategy into the gradi-ent descent step of the Proximal Gradient Descent (PGD) algorithm, driving it to deal with complex and real-world image degradation. In addition, we design inter-stage in-formation pathways across proximal mapping in different PGD iterations to rectify the intrinsic information loss in most deep unfolding networks (DUN) through a multi-scale and spatial-adaptive way. By integrating the flexible gradi-ent descent and informative proximal mapping, we unfold the iterative PGD algorithm into a trainable DNN. Exten-sive experiments on various image restoration tasks demon-strate the superiority of our method in terms of state-of-the-art performance, interpretability, and generalizability. The source code is available at github.com/MC-E/DGUNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI