Supercharge Your Innovation With Domain-Expert AI Agents!

De-noising images drawn using monte carlo drawing

An image and pixel technology, applied in the field of image denoising using the Monte Carlo method, can solve problems such as large computational burden

Pending Publication Date: 2022-05-27
ADOBE SYST INC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Complicating this issue is the fact that the relatively large number of sampling points results in a non-trivial computational burden

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
  • De-noising images drawn using monte carlo drawing
  • De-noising images drawn using monte carlo drawing
  • De-noising images drawn using monte carlo drawing

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0226] Example 1. A method for denoising an image, the method comprising: identifying a plurality of corresponding sampling points within individual pixels in a set of pixels of a first image; for the individual sampling points, estimating the Corresponding radiation vectors of light received at; generating corresponding intermediate radiation features for individual pixels in the set by the first machine learning module, based at least in part on radiation vectors associated with a plurality of corresponding sampling points within the corresponding pixels a vector; generating, by the second machine learning module, a corresponding final radiance feature vector for individual pixels in the set based at least in part on the intermediate radiance feature vector of the corresponding pixel and one or more adjacent pixels; and based at least in part on the final radiance feature vector to generate a second image, wherein the second image has less noise and is more realistic than the...

example 2

[0227] Example 2. The method of example 1, wherein: generating a final radiation feature vector comprises: generating, for each pixel in the set, a corresponding final radiation feature vector having at least a corresponding first segment and a corresponding second segment; and The method also includes generating a first subset of kernels with a first magnitude based at least in part on the first segment of the final radiation eigenvectors, and generating a first subset of the kernels with a first magnitude based at least in part on the second segment of the final radiation eigenvectors Second kernel subset of two strides.

example 3

[0228] Example 3. The method of Example 2, wherein generating the first subset of kernels includes generating a first kernel in the first subset of kernels, the first kernel including a first pixel as the target pixel and a plurality of adjacent to the target pixel pixel, where the first kernel has a stride X, indicating that pixels within the first kernel that are X pixels away from the target first pixel are assigned a non-zero weight, X is a positive integer, and the second pixel within the first kernel is the same as the target first pixel The pixels are X pixels apart, and wherein the first weight specifying the contribution of the radiation value from the second pixel to the first pixel is based, at least in part, on (i) the first segment of the first final radiation eigenvector for the first pixel and the (ii) is calculated for the distance between the first segments of the second final radiation eigenvector for the second pixel.

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

Embodiments of the present disclosure relate to de-noising an image drawn using Monte Carlo drawing. A plurality of pixel-based sampling points are identified within the image, wherein sampling points of a pixel are distributed within the pixel. For individual sampling points of individual pixels, corresponding radiation vectors are estimated. The radiation vector includes one or more radiation values characterizing the light received at the sampling point. A first machine learning module generates a corresponding intermediate radiation feature vector for each pixel based on radiation vectors associated with sampling points within the pixel. A second machine learning module generates a corresponding final radiation feature vector for each pixel based on the intermediate radiation feature vector for the pixel and one or more other intermediate radiation feature vectors for one or more other pixels adjacent to the pixel. One or more kernels are generated based on the final radiation feature vector and applied to corresponding pixels of the image to generate a lower noise image.

Description

technical field [0001] The present disclosure relates generally to denoising of images, and more particularly to techniques for denoising images rendered using Monte Carlo methods. Background technique [0002] Over the past few years, with advances in computer graphics, composite images can be generated using computers. For example, an image processing application may be used to digitally generate a composite image from a composite or virtual scene, where the scene includes various digitally generated objects. Often, such composite images may not look realistic due to the lack of lighting effects in the composite scene. A scene file describes a virtual scene with information about geometry, lighting, shadows, viewpoint, and / or other properties. The process of adding lighting effects to a composited scene to make the resulting composited image look realistic is often referred to as photorealistic rendering of the composited scene, or, for the purposes of this disclosure, i...

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): G06T5/50G06T5/00G06N3/08
CPCG06T5/50G06N3/08G06T2207/20081G06T2207/20216G06T5/70G06T5/20G06T2207/20084G06T2207/20076G06N7/01G06N3/045G06T5/60G06N20/00G06V10/56G06V10/60G06T3/40
Inventor M·伊西克M·格哈比M·费希尔K·B·M·拉克什米纳拉亚纳J·埃森曼F·派拉兹
Owner ADOBE SYST INC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com