Scalable Monte Carlo image synthesis

1997 ◽  
Vol 23 (7) ◽  
pp. 845-859 ◽  
Author(s):  
Alan Heirich ◽  
James Arvo
Keyword(s):  
Monte Carlo ◽  
Image Synthesis

Adaptive Sampling Based on GH-Distance for Realistic Image Synthesis

2014 ◽  
Vol 998-999 ◽  
pp. 806-813
Author(s):  
Jian Wang ◽  
Qing Xu
Keyword(s):  
Monte Carlo ◽  
Computer Graphics ◽  
Adaptive Sampling ◽  
Random Noise ◽  
Image Synthesis ◽  
Simulation Methods ◽  
Path Tracing ◽  
Complex Scenes ◽  
Realistic Image ◽  
Better Than

Realistic image synthesis technology is an important part in computer graphics. Monte Carlo based light simulation methods, such as Monte Carlo path tracing, can deal with complex lighting computations for complex scenes, in the field of realistic image synthesis. Unfortunately, if the samples taken for each pixel are not enough, the generated images have a lot of random noise. Adaptive sampling is attractive to reduce image noise. This paper proposes a new GH-distance based adaptive sampling algorithm. Experimental results show that the method can perform better than other similar ones.

Monte Carlo Methods for Image Synthesis

2018 ◽  
pp. 7-17
Author(s):  
André Bigand ◽  
Julien Dehos ◽  
Christophe Renaud ◽  
Joseph Constantin
Keyword(s):  
Monte Carlo ◽  
Monte Carlo Methods ◽  
Image Synthesis

Spatial Resolution Optimization of Backscattered Electron Images Using Monte Carlo Simulation

2012 ◽  
Vol 18 (3) ◽  
pp. 628-637 ◽  
Author(s):  
Camille Probst ◽  
Hendrix Demers ◽  
Raynald Gauvin
Keyword(s):  
Monte Carlo ◽  
Spatial Resolution ◽  
Synthesis Method ◽  
Image Synthesis ◽  
Feature Size ◽  
Probe Size ◽  
Electron Image ◽  
Backscattered Electron ◽  
The Fourier Transform ◽  
Simulated Images

AbstractThe relation between probe size and spatial resolution of backscattered electron (BSE) images was studied. In addition, the effect of the accelerating voltage, the current intensity and the sample geometry and composition were analyzed. An image synthesis method was developed to generate the images from backscattered electron coefficients obtained from Monte Carlo simulations. Spatial resolutions of simulated images were determined with the SMART-J method, which is based on the Fourier transform of the image. The resolution can be improved by either increasing the signal or decreasing the noise of the backscattered electron image. The analyses demonstrate that using a probe size smaller than the size of the observed object (sample features) does not improve the spatial resolution. For a probe size larger than the feature size, the spatial resolution is proportional to the probe size.

scholarly journals A survey on deep learning-based Monte Carlo denoising

2021 ◽  
Vol 7 (2) ◽  
pp. 169-185
Author(s):  
Yuchi Huo ◽  
Sung-eui Yoon
Keyword(s):  
Monte Carlo ◽  
Deep Learning ◽  
Image Synthesis ◽  
Post Processing ◽  
Sampling Schemes ◽  
Reconstruction Scheme ◽  
Real World Applications ◽  
Estimator Bias ◽  
Recent Trends ◽  
Realistic Image

AbstractMonte Carlo (MC) integration is used ubiquitously in realistic image synthesis because of its flexibility and generality. However, the integration has to balance estimator bias and variance, which causes visually distracting noise with low sample counts. Existing solutions fall into two categories, in-process sampling schemes and post-processing reconstruction schemes. This report summarizes recent trends in the post-processing reconstruction scheme. Recent years have seen increasing attention and significant progress in denoising MC rendering with deep learning, by training neural networks to reconstruct denoised rendering results from sparse MC samples. Many of these techniques show promising results in real-world applications, and this report aims to provide an assessment of these approaches for practitioners and researchers.

Sign in / Sign up

Export Citation Format

Share Document