Image-based re-lighting method

A technology of heavy lighting and images, applied in the field of machine learning and graphics, can solve the problems of increasing work intensity and storage space, and achieve the effect of less image samples, less training time, and high PSNR value

Inactive Publication Date: 2017-04-19
HOHAI UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] IBR often needs to obtain image samples through dense sampling, which greatly increases the work intensity and storage space

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-based re-lighting method
  • Image-based re-lighting method
  • Image-based re-lighting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0032] An image-based re-illumination method of the present invention, such as figure 1 shown, including:

[0033] Step 1: Collect a set of three-dimensional scene data (Dagon, Mitsuba), including the LigX and LigY coordinates of the point light source and the corresponding image set ImageSet output at a fixed viewpoint; calculate the average of the image set in the three channels of R, G, and B Value, get ImgAvg_R, ImgAvg_G, ImgAvg_B; scene data is shown in Table 1.

[0034] Table 1 scene data

[0035] Scenes Light source distribution image size dragon 31×31 64×48 Mitsuba 21×21 64×48

[0036] Step 2: Randomly sample in the image set ImageSet to form the image subset ImageSubset, and the number of image samples is ImageNum.

[0037] Step 3: Randomly sample the pixels of the image subset like ImageSubset to obtain...

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 present invention discloses an image-based re-lighting method and belongs to the computer graphics field. In order to achieve re-lighting as accurately as possible with as few samples as possible, quantitative random sampling is performed repeatedly in the spaces of image samples and image pixels, and training is performed through using an artificial neural network until the training accuracy of all pixels reaches a set threshold value; and provided that the artificial neural network has a requirement for minimum samples in training, the Bagging algorithm of ensemble learning is utilized to perform averaging processing on pixel training samples when the pixel training samples are insufficient. The method of the present invention is tested in a simulated three-dimensional scene, and a test result indicates that the image-based re-lighting method has the advantages of less training time and high robustness as well as fewer image samples, high speed, excellent real-time performance and high PSNR (peak signal to noise ratio) of a reconstructed scene image under the same relative error accuracy compared with the prior art.

Description

technical field [0001] The invention relates to an image-based re-illumination method, belonging to the fields of machine learning and graphics. Background technique [0002] Image-based Relighting (Image-based Relighting, IBR), also known as Image-based Rendering, its purpose is to start from the captured image, calculate the light transmission matrix and draw the new light source conditions scene image. Its biggest advantage is that it does not require the geometric information of the scene, the rendering is not affected by the complexity of the scene, and it can also express various lighting effects such as reflection, refraction, and scattering. Therefore, since IBR was proposed, it immediately became the focus of attention in the field of graphics. [0003] IBR often needs to obtain image samples through dense sampling, which greatly increases the work intensity and storage space. Whether the machine learning method can be used to achieve image-based re-illumination ...

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): G06T15/20G06N3/04G06N3/08
CPCG06N3/08G06T15/205G06N3/045
Inventor 韦伟刘惠义钱苏斌
Owner HOHAI UNIV
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