DeepAI AI Chat
Log In Sign Up

Deep Graph Laplacian Regularization

07/31/2018
by   Jin Zeng, et al.
0

We propose to combine the robustness merit of model-based approaches and the learning power of data-driven approaches for image restoration. Specifically, by integrating graph Laplacian regularization as a trainable module into a deep learning framework, we are less susceptible to overfitting than pure CNN-based approaches, achieving higher robustness to small dataset and cross-domain denoising. First, a sparse neighborhood graph is built from the output of a convolutional neural network (CNN). Then the image is restored by solving an unconstrained quadratic programming problem, using a corresponding graph Laplacian regularizer as a prior term. The proposed restoration pipeline is fully differentiable and hence can be end-to-end trained. Experimental results demonstrate that our work avoids overfitting given small training data. It is also endowed with strong cross-domain generalization power, outperforming the state-of-the-art approaches by remarkable margin.

READ FULL TEXT
07/18/2018

Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding

State-of-the-art approaches toward image restoration can be classified i...
02/11/2021

Learning local regularization for variational image restoration

In this work, we propose a framework to learn a local regularization mod...
01/13/2022

Convolutional dual graph Laplacian sparse coding

In recent years, graph signal processing (GSP) technology has become pop...
04/27/2016

Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain

Inverse imaging problems are inherently under-determined, and hence it i...
12/20/2016

Deeply Aggregated Alternating Minimization for Image Restoration

Regularization-based image restoration has remained an active research t...
03/11/2020

BP-DIP: A Backprojection based Deep Image Prior

Deep neural networks are a very powerful tool for many computer vision t...
04/26/2018

CD-CNN: A Partially Supervised Cross-Domain Deep Learning Model or Urban Resident Recognition

Driven by the wave of urbanization in recent decades, the research topic...