Non-Local Sparse Representation Method for Demosaicing of Single DoFP Polarimetric Image

Ruinan Wang,Wei Gao,Fengtao Wang,Chao Shen

IEEE International Conference on Communication Software and Networks (ICCSN)（2020）

Cited 2|Views14

Abstract

The images in different polarization directions collected from division-of-focal-plane (DoFP) imaging system are under-sampled. To solve the demosaicing problem of DoFP imaging, this paper presents a learning model based on sparse representation to optimize the interpolation result of DoFP images. Firstly, image blocks rich in edge or texture information are selected according to the local gradient, and these blocks are clustered based on non-local similarity to learn a sub-dictionary from each class adaptively. The model uses local similarity and sparsity of coding coefficients as regularization terms to minimize coding errors, and then the algorithm iteratively optimizes dictionary atoms and coding coefficients alternately to obtain enhanced images. The experiment takes 8 composed DoFP images as reference and compares the interpolation results of the proposed algorithm with different methods. The proposed method obtains smaller interpolation error than other methods at every image in the experiment.

Translated text

Key words

polarimetric image,sparse representation,image demosaicing

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper