Efficient and Stable Generation of High-Resolution Hair and Fur With ConvNet Using Adaptive Strand Geometry Images

Efficient and Stable Generation of High-Resolution Hair and Fur With ConvNet Using Adaptive Strand Geometry Images

This paper proposes a technique for transforming low-resolution (LR) simulations of hair and fur into high-resolution (HR) representations without noise, using strand geometry images in the form of lines and Convolutional Neural Network (CNN or ConvNet). LR and HR data for training are obtained thro...

Full description

Bibliographic Details
Main Authors: Jong-Hyun Kim, Jung Lee
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Hair simulation
fur simulation
convolutional neural network
physically based simulation
strand geometry image
adaptive hairs
Online Access:https://ieeexplore.ieee.org/document/10201851/

Internet

https://ieeexplore.ieee.org/document/10201851/

Similar Items