Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image high dynamic range reconstruction method based on deep learning

A high dynamic range, deep learning technology, applied in neural learning methods, image enhancement, image analysis, etc., can solve problems such as the limitation of brightness level invariant reconstruction effect, and achieve good reconstruction effect

Active Publication Date: 2020-06-16
WUHAN UNIV
View PDF7 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some scholars have also done some fruitful work based on deep learning, but they failed to take into account factors such as the invariance of brightness levels between HDR pictures, which lead to limitations in the reconstruction effect

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image high dynamic range reconstruction method based on deep learning
  • Image high dynamic range reconstruction method based on deep learning
  • Image high dynamic range reconstruction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] Such as figure 1 As shown, the present invention is a deep learning-based image high dynamic range reconstruction method, comprising the following steps:

[0049] Step 1, preprocess the HDR dataset to construct the training data for the neural network. Firstly, LDR data is generated from the collected HDR data set, then the LDR-HDR data is used to align the HDR data, and then the aligned HDR image is used to generate a highlight mask image, and finally the three are integrated as the training data of the neural network. The LDR data is the data input, and the aligned HDR data and highlight mask image are the label data.

[0050] Step 2, constructing and training the neural network to obtain a network model with a mapping relationship from LDR to HDR. According to the training strategy, the generator network and the d...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an image high dynamic range reconstruction method based on deep learning, and belongs to the field of computational photography and digital image processing. A mapping networkfrom a single LDR image to an HDR image is established by adopting a method based on deep learning. The method comprises the steps of generating LDR training data, HDR sample tags with aligned brightness units and mask images of high-brightness areas sequentially from a collected HDR data set; and then constructing and training a neural network to obtain a network model with an LDR-to-HDR mappingrelationship; and finally, directly inputting the LDR image into the network model by using the trained generative network model, thereby outputting the reconstructed HDR image. According to the method, the dynamic range of a real scene can be effectively reconstructed from a single common digital image, and the method can be used for HDR simulation effect display of the common digital image or providing a more realistic rendering effect for an image-based lighting technology.

Description

technical field [0001] The invention belongs to the field of computational photography and digital image processing, and relates to an image high dynamic range reconstruction method, in particular to an image high dynamic range reconstruction method based on deep learning. Background technique [0002] High Dynamic Range Imaging (HDRI) technology is an image representation method used to achieve a larger exposure range than ordinary digital images. High Dynamic Range (HDR) images can provide more A large range of brightness changes and more details of light and shade enable HDR images to present brightness change information that is closer to the real scene. In recent years, with the continuous evolution of display devices and the increasing demand for physically based rendering, high dynamic range imaging technology has become more and more important in practical applications. However, current methods of directly acquiring HDR images require high professional skills, are c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/20208G06N3/045G06T5/90Y02T10/40
Inventor 肖春霞刘文焘
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com