Explore computer vision and deep learning applications in gaming through this 29-minute webinar featuring Srinath Sridhar. Delve into topics such as full body posture estimation, hand pose detection, object reconstruction, and neural network architectures for 3D modeling. Discover how these technologies are revolutionizing gaming experiences, from Microsoft Flight Simulator to context-aware mixed reality. Gain insights into the challenges and goals of implementing computer vision in gaming, and understand the differences between computer vision and computer graphics. Learn about synthetic data generation and its role in advancing gaming pipelines. Conclude with a comprehensive summary of the state of computer vision in gaming and its future potential.
3D Deep Learning for Gaming with Srinath Sridhar and Stanford Artificial Intelligence
Resemble AI via YouTube
Overview
Syllabus
Introduction
Overview
Goals
Challenges
Outline
Understanding Humans
Full Body Posture
Goal
Example
More examples
Gaming applications
YouTube videos
Hands
Objects
Reconstructing Objects
Neural Network Architecture
Mesh parametric mesh reconstruction
Car reconstruction
Microsoft Flight Simulator
The State of Computer Vision
Computer Vision vs Computer Graphics
Hand Pose Estimation
Hand Pose Estimation Example
Virtual Cars
ContextAware Mixed Reality
Synthetic Data
Gaming Pipeline
Conclusion
Summary
Thank you
Taught by
Resemble AI
