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

A multi-overlay variable support and order kernel-based representation for image deformation and view synthesis

一种图像变形、覆盖层的技术,应用在图像变形信息的表示领域,能够解决背景缠结、不能够处置半透明的和反射的对象等问题,达到优化尺度、压缩率增加、高效压缩的效果

Active Publication Date: 2018-04-17
VERSITECH LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Furthermore, since conventional depth maps contain only one value at a specific location, image domain warping methods may not be able to handle semi-transparent and reflective objects because the objects are entangled with the background

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
  • A multi-overlay variable support and order kernel-based representation for image deformation and view synthesis
  • A multi-overlay variable support and order kernel-based representation for image deformation and view synthesis
  • A multi-overlay variable support and order kernel-based representation for image deformation and view synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Mathematical basis

[0031] Consider a pixel i(x,y) of an image I with resolution MxN, where M is the number of pixel columns (width) and N is the number of pixel rows (height). x=1,2,...M and y=1,2,...N are the x and y coordinates of the pixel. Conventionally, the image deformation for each pixel i(x,y) can be expressed as a displacement denoted by d(x,y). They can be rewritten in matrix form

[0032] D=[d 1 , d 2 ,...,d M ], where d x =[d(x,1),d(x,2),...,d(x,N)] T (1)

[0033] In view synthesis, the position of the original pixel i(x,y) in the V views is computed. The new position at the vth view is i v (x,y), where v=1,2,...,V. at i v In the conventional representation of (x,y), i v The relationship between (x,y) and i(x,y) is given as

[0034] i v (x,y)=φ(x,y,v)=φ(i(x,y),d(x,y),v) (2)

[0035] where φ(.) is a composition function that modifies the position of i(x,y) to synthesize the vth view of I. See Stefanoski and Kauff et al., "Depth map creation ...

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 technique for displaying 3D videos creates a representation of image deformation, such as depth maps, in terms of a function for overlaying kernels with variable support and order. By optimizing thekernel type, order and support, which are allowed to be varied across different region of the deformation, it is able to approximate the image deformations in terms of the kernel parameters. Since the number of kernel parameters is usually much smaller than that of the number of pixels, this allows a significant reduction in the storage size of the image deformation.

Description

technical field [0001] The present invention relates to the representation of image warping information in the formation, transmission and storage of three-dimensional images in applications such as image registration, video processing and view synthesis. Background technique [0002] Most visual content today is still in two-dimensional (2D) images or video in the form of a sequence of images. In general, conventional images and videos do not support changes in viewpoint other than mere scaling or simple shifting. With the advent of stereoscopic or three-dimensional display technology, active shutter and passive polarized glasses are now commonly available. More recently, high resolution autostereoscopic displays that do not require glasses have become available. The input to such an autostereoscopic display is usually i) the video plus a depth map describing the depth of each pixel in the video, or (ii) a collection of videos at neighboring viewpoints, sometimes called m...

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): H04N13/111H04N13/161
CPCH04N2013/0085H04N13/111H04N13/161H04N13/128H04N21/488
Inventor 陈成就胡皓竣
Owner VERSITECH LTD
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