An Improved High Dimensional Space Adaptive Sampling Method

An adaptive sampling and high-dimensional space technology, applied in the field of image processing, can solve the problems of inability to scale, overall image distortion, uneven distribution of sampling points, etc., achieve good adaptability, expand sampling space, and solve overall image distortion Effect

Active Publication Date: 2019-04-02
SHANGHAI JIAOTONG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on the one hand, this method cannot adapt well to the scaling of different dimensions, and on the other hand, the overall image distortion is caused by the uneven distribution of sampling points.

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
  • An Improved High Dimensional Space Adaptive Sampling Method
  • An Improved High Dimensional Space Adaptive Sampling Method
  • An Improved High Dimensional Space Adaptive Sampling Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is carried out on the premise of the technical solution of the present invention, and detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0029] Such as figure 1 As shown, this embodiment provides an improved high-dimensional space adaptive sampling method for spatially reconstructing an image, and the method includes the following steps:

[0030] 1) Random sparse sampling in high-dimensional space;

[0031] 2) Use the adaptive scale estimation method to selectively encrypt the sampling points of the random sparse sampling in step 1):

[0032] 21) evenly divide the sampling points into B buckets along the dimension, and the value of B in this embodiment is 10;

[0033] 22) Statistics the variance of each bucket;

[...

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 relates to an improved high-dimension space adaptive sampling method used for space reconstruction of an image. The method includes following steps: performing random sparse sampling in a high-dimension space; performing selective encryption sampling on sampling points for random sparse sampling by employing an adaptive scale estimation method; eliminating distortion caused by selective encryption sampling; reconstructing a brightness function of the high-dimension space according to brightness values of the sampling points for encryption sampling; performing integral reconstruction on a non-image space dimension in the reconstructed brightness function, and obtaining a brightness function in the final image dimension; and processing the brightness function in the final image dimension, and performing space reconstruction on the image. Compared with the prior art, the method is advantaged by good reconstruction effect, high adaptability, wide application range, and avoidance of distortion etc.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an improved high-dimensional space adaptive sampling method. Background technique [0002] The ray tracing algorithm used in the high-realistic image rendering technology mainly consists of three parts: sampling the dimensions corresponding to the camera and the scene to generate the light path connecting the light source and the camera; calculating the brightness corresponding to the light path; according to the sampling information and the corresponding light path The brightness information is used to reconstruct the image. [0003] The physical model involved in the calculation of the brightness of the light path is based on the energy-conserving lighting brightness drawing equation and the bidirectional reflection distribution function. The former gives the mathematical formula expression of the brightness of the outgoing light at a certain point relative to the brig...

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 Patents(China)
IPC IPC(8): G06T15/06G06T15/50
CPCG06T15/06G06T15/506G06T2215/06
Inventor 盛斌杨欢
Owner SHANGHAI JIAOTONG 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