Home › Categories › Technology› 1-s2.0-S009784932200 1820-main.pdf

1-s2.0-S009784932200 1820-main.pdf

1-s2.0-S0097849322001820-main.pdf

🔗 Source: open.metu.edu.tr

📊 Size: 1.99 MB

📄 Pages: 10 pages

⬇️ Downloads: 48

Summary

Researchers developed a method to generate 3D human models from 2D stick figure sketches using Variational Autoencoders, without requiring a statistical body shape model. The network learns the mapping between the input sketch and the output 3D model, and can also generate 3D animations through interpolation and extrapolation in the learned embedding space. The method is capable of producing visually appealing 3D point cloud models and dynamic 3D models, and has been extended to generate 3D horse models, demonstrating its generalization ability.

Download File

Description

Researchers developed a method to generate 3D human models from 2D stick figure sketches using Variational Autoencoders, without requiring a statistical body...

Technical Information

File Format: PDF
File Size: 1.99 MB
Pages: 10
Language: EN
Total Downloads: 48
Last Updated: 6 days ago

Document Overview

This PDF document about 1-s2.0-S009784932200 1820-main.pdf provides comprehensive information and guidance. Whether you're a beginner or advanced user, this resource offers valuable insights into 1-s2.0-S009784932200 1820-main.pdf.