Adaptive rendering method based on weight local regression

An adaptive rendering and local regression technology, applied in 3D image processing, image data processing, instruments, etc., can solve the problem that the image space has not been paid attention to

Inactive Publication Date: 2016-04-20
ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these issues have received little attention in existing image space adaptive rendering methods that exploit these features

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
  • Adaptive rendering method based on weight local regression
  • Adaptive rendering method based on weight local regression
  • Adaptive rendering method based on weight local regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] The present invention will be described in detail below in conjunction with the accompanying drawings and specific implementation examples. This embodiment is implemented using CUDA on the basis of pbrt2 (physical rendering system based on ray tracing). Accumulate the feature and color buffers in each sample phase and store the buffers in the GPU's texture memory to run the reconstruction. A CUDA implementation of Jacob's iteration is used to compute the SVD.

[0086] A truncated singular value decomposition (TSVD) is performed on the input image to compute a reduced feature space of the input image.

[0087] Given an input image, as shown in Figure 1(a), the local dimension is calculated according to TSVD, and the result is shown in Figure 1(b).

[0088] See Fig. 1(c) and Fig. 1(d) when using smaller and larger matrix rank reconstructed images, respectively, which exhibit overly blurred artifacts in in-focus regions and noise in out-of-focus regions.

[0089] Howeve...

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 discloses an adaptive rendering method based on weight local regression. The method comprises the following specific steps: filtering and reconstructing an image by use of local regression; constructing a simplified feature space by use of truncated singular value decomposition (TSVD) so as to eliminate noise carried by a feature vector; respectively predicating an optimal feature bandwidth bj and a shared bandwidth h by use of a two-step bandwidth selection algorithm; and distributing available light samples to areas with high errors by use of an iteration method based on a local simplified feature subspace k. The method provided by the invention is a novel adaptive rendering technology and can be applied to processing rendering effects of multiple types in an efficient and robust manner. Compared to prior similar arts, the method has the following advantages: the time for generating results with the same quality is obviously reduced, and the result image effect generated based on equal calculation time and calculation cost is far better than that of the similar arts.

Description

technical field [0001] The invention relates to the technical field of computer image processing, and relates to an adaptive rendering image reconstruction method based on weighted local regression. Background technique [0002] Adaptive rendering methods and Monte Carlo ray tracing have a long history of reconstructing images. Current work has also made greater progress in this area, but the main goal remains the same: to improve image quality with a smaller number of ray samples for greater efficiency. Images generated from too few ray samples are prone to noise and are slow to aggregate into a smooth image. A key element of adaptive sampling and reconstruction is the local implementation of error analysis, which guides rays to focus on high-error regions when controlling smoothing for image reconstruction to produce numerically and visually pleasing rendering results. [0003] In high dimensions, adaptive rendering techniques can be divided into integral methods and ima...

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): G06T15/00
CPCG06T15/00
Inventor 张根源
Owner ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
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