Object image relighting method based on block-matching transformation and color transfer

A technology of color migration and object image, which is applied in the field of computer vision and visual computing, can solve problems such as time-consuming, and achieve the effects of saving running time, strong robustness, and simple structure

Active Publication Date: 2017-01-04
BEIJING ELECTRONICS SCI & TECH INST
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this high-intensity matching consumes a lot of time

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
  • Object image relighting method based on block-matching transformation and color transfer
  • Object image relighting method based on block-matching transformation and color transfer
  • Object image relighting method based on block-matching transformation and color transfer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0041] Block matching deformation process:

[0042] The input object image I and the two color-changed reference object images A' and B' are used as the input of the local and global illumination transfer process of the present invention. In actual operation, these three images exist in the form of a matrix.

[0043] For a square block of length 2r+1, use L 2 norm. For the relationship between pixel p∈I and its corresponding pixel q∈A, it can be simplified to the following formula:

[0044] Σ i = - r r Σ j = - r r | | I ( x p + i , y p ...

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 provides an object image relighting method based on block-matching transformation and color transfer. A block-matching algorithm and a color transformation algorithm are combined with local and global lighting transfer models; on the premise of keeping the lighting condition of a reference image constant, the color of the reference image is changed by the color transformation algorithm, so that the color of the reference image is consistent with the color of an input image; and since colors have relatively great influences on image lighting transfer, the influences of the colors on later lighting transfer processing can be lowered greatly in the above way. After the influences of color factors on results are lowered greatly, the reference image is deformed by the block-matching algorithm, so that the shape of the reference image is matched with an object in the input image. Finally, the input image and the transformed reference image are subjected to lighting transfer through local and global affine transformation, so that relighting of the input image is finished. The method is very easy to implement through software, and can be popularized and applied to a wide variety of fields such as computer vision, visual design, digital entertainment and film producing.

Description

technical field [0001] The invention belongs to the fields of visual computing and computer vision, in particular to an object illumination transfer method, specifically an illumination transfer method based on local and global affine transformation models. 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...

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): G06T7/40G06T15/50
CPCG06T15/50
Inventor 金鑫田玉露李玉珍叶超尘池经营李晓东赵耿
Owner BEIJING ELECTRONICS SCI & TECH INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap