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

Large-scale decomposition-based outdoor scene relighting method

A large-scale, re-illumination technology, applied in the field of visual computing and computer vision, can solve the problems of complex lighting in outdoor scenes, large-scale outdoor scenes, and difficulty in establishing geometric models, so as to save operating space, reduce invention costs, and structure simple effect

Active Publication Date: 2018-03-23
中共中央办公厅电子科技学院
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with indoor lighting estimation, outdoor scenes have two characteristics, and these two characteristics are also two main challenges faced in the lighting estimation of outdoor scenes: (1) Outdoor scenes are generally large in scale, and it is difficult to establish their geometric models
(2) The lighting of outdoor scenes is complex and cannot be controlled artificially
The previous invention did not work well when breaking down materials and ambient light colors

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
  • Large-scale decomposition-based outdoor scene relighting method
  • Large-scale decomposition-based outdoor scene relighting method
  • Large-scale decomposition-based outdoor scene relighting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0046] Block matching deformation process:

[0047] The input image is A, the reference image is B, and the deformed reference image is used as the input of the large-scale decomposition process of the present invention. In actual operation, these three images exist in the form of a matrix.

[0048] NNF (Nearest Neighbor Field, NNF for short) is initialized as a random value or known information. When using random offsets, an independent uniform sampling of the entire region of image B is taken. NNF is the equation:

[0049]

[0050] Its domain of definition is the coordinates of all blocks in image A. The value of the equation is the coordinate offset of the matching block relative to the query block. If the block with coordinate a in image A matches the block with coordinate b in image B, then:

[0051] f(a)=b-a (2)

[0052...

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

A large-scale decomposition-based outdoor scene relighting method provided by the present invention comprises the steps of processing an input image, coloring the image according to the materials andthe content in the image, manually generating a mask image of the input image, and then for a reference image, selecting a Patch_match method to match and deform the reference image, and decomposing the brightness layers of the input image and the reference image into the large-scale layers and the detail layers separately according to the given adaptive parameter selection mechanisms and by utilizing a weighted least square (WLS) filter, and under the guidance of the large-scale layer of the input image, carrying out the guided filter on the large-scale layer of a reference object, so that the filter result aligns at the large-scale layer of an input object structurally, and further the rendering is realized. By a point division algorithm, the fusion of the detail layers and the large-scale layers of the pre-outputted images is realized, and a final relighting result is obtained. The method is very easy to realize by a software.

Description

technical field [0001] The invention belongs to the fields of visual computing and computer vision, and in particular relates to a large-scale decomposition-based re-illumination method for outdoor scenes. Background technique [0002] Image-based realistic virtual relighting without 3D models has been widely studied in the field of visual computing, and has been widely used in visual design, digital entertainment, and film production. [0003] Image-based virtual relighting can be roughly divided into the following categories: face relighting, scene relighting and object relighting. In addition to 3D reconstruction theory, another research direction is to use reference images for more practical applications in real-world applications. In this direction, face re-illumination is the most common research direction. The source of the reference image ranges from multiple face reference images, to two face reference images and then to a single face reference image. Scene relig...

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): G06T5/50G06T15/50
CPCG06T5/50G06T15/50G06T2207/20028
Inventor 金鑫李艳楠李晓东田玉露吴乐刘晶
Owner 中共中央办公厅电子科技学院
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