A photon mapping rendering method and system based on neural network

A neural network and photon mapping technology, applied in the field of neural network-based photon mapping rendering methods and systems

Active Publication Date: 2019-03-22
PEKING UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the core problem of progressive photon mapping is that each rendered image requires thousands o...

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 photon mapping rendering method and system based on neural network
  • A photon mapping rendering method and system based on neural network
  • A photon mapping rendering method and system based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below through specific embodiments and accompanying drawings.

[0035] The invention designs a neural network applied to the problem of photon mapping rendering synthesis. The key issues involved in solving the theory and method of photon mapping through neural networks are as follows: First, the problem of photon mapping synthesis belongs to dense prediction (dense prediction) problem, which does not require batch normalization layer (Batch Normalization, BN) ; The second is that the photon mapping synthesis problem needs to solve the noise caused by too small radius, and the blur problem caused by too large radius; the third is that the photon mapping synthesis problem is suitable for using a fully convolutional neural network, because this problem is related to the surrounding pixels The value of is more relevant and less sensitive to global information.

[0036] 1. The input data set of the neural network

...

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 a photon mapping rendering method and a system based on a neural network. The method comprises the following steps: 1) adopting a photon mapping method to generate k color effect images with different rendering quality; 2) inputting a plurality of training set composed of k color effect images with different rendering quality into a neural network for training to obtain aneural network model; 3) synthesizing a global lighting render image based on that neural network model. Compared with the existing progressive photon mapping method, the invention requires only the intermediate rough results produced by several iterative photon mappings, The neural network proposed by the invention can be used to infer the rendering result of synthesizing the convergence of the progressive photon mapping, thereby solving the problem that the traditional progressive photon mapping method needs a large number of iterations which are very time-consuming to generate a more idealrendering result.

Description

technical field [0001] The invention belongs to the technical field of computer graphics, and in particular relates to a neural network-based photon mapping rendering method and system. Background technique [0002] Global illumination image generation is an important field of computer graphics. The key is how to add more realistic lighting effects to 3D scenes. The photon mapping algorithm is a classic global illumination algorithm in computer graphics, which can draw more realistic caustics and other phenomena, but a serious disadvantage is that the required drawing time is very long. [0003] In the traditional highly realistic global illumination calculation and rendering methods, the photon mapping method is one of the representative methods. Progressive photon mapping (Hachisuka, T., Ogaki, S., and Jensen, H.W. Progressive photon mapping. ACM Transactions on Graphics (TOG) 27, 5 (2008), 130.) is the most mainstream solution for photon mapping methods at present. fra...

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
IPC IPC(8): G06T15/50G06T15/04
CPCG06T15/04G06T15/506G06T2207/20081G06T2207/20084Y02D10/00
Inventor 林泽辉李胜汪国平
Owner PEKING 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