mobile off
ABOUT US  |  RESEARCH  |  PUBLICATION   |  COURSE  |  SEMINAR  |  LINKS
Research
Physically-Based Simulation
Fluid Interaction
Fire
Ice and Snow
Water
Smoke
Shell Deformation
User Behavior Analysis
Sentiment Analysis
Outlier Detection
Automatic Player Behavior Analysis
Adaptive Agent Navigation
Crowd Simulation
Graphics Applications
Neuroimage
Artificial Life
3D Geometry Processing
Real domain data visualization
Integral MLS Surface Model
SDF-based Geometry Synthesis
Point-based Geometry and Modeling
Texture Processing
Multi-exemplar Inhomogeneous Texture Synthesis

1. Abstract

This paper presents a new framework for the semi-automatic synthesis of an inhomogeneous texture from a theoretically infinite number of input exemplars. Our algorithm generates a result with natural multiway transitions, maintaining a reasonable synthesis time to keep interactivity. We introduce intermediate textures between multiple exemplars, called ‘transition textures’ which enables our algorithm to produce smooth transitions between input exemplar patches. We also propose ‘image index correction’ to achieve a synthesis speed that is independent of the number of input exemplars by smart placement of transition-texture samples. Our algorithm is semiautomatic, spatially deterministic and well suited to acceleration via parallel processors. Also, our algorithm can easily control the synthesis result to design a texture visual with user interactions.

 
 

2. Publication

Hanwook Park and Chang-Hun Kim, "Multi-exemplar Inhomogeneous Texture Synthesis," Computer & Graphics, 2013

 
 

3. Results



Result 1 : Air bubble shapes like needles.
The bubbles formed will align to a direction similar to the direction of the ice growth





Result 2 : Progressive Result: (Top left) Without any opaque area (Top right) Using particle only (Bottom left) Dissolved air field only (Bottom right) Both particles and the field



ABOUT_US  |  RESEARCH  |  PUBLICATION  |  COURSE  |  SEMINAR  |  LINKS