EA Technology AI & Machine Learning Animation Speech & Language Rendering & Lighting SEED Frostbite All Teams AI & Machine Learning Animation Speech & Language Rendering & Lighting SEED Frostbite All Teams

SEED Presentations at SIGGRAPH 2021

SIGGRAPH 2021

SEED is well-represented at SIGGRAPH 2021. We have three presentations from developers at SEED showcasing some of our most exciting recent work. The videos of the presentations will also be posted here on the SEED website.

Following is an overview of the talks we are doing at SIGGRAPH 2021:

Swish: Neural Network Cloth Simulation on Madden NFL 21

Talk by SEED’s Christopher Lewin

This work presents Swish, a real-time, machine-learning-based cloth simulation technique for games. Swish was used to generate realistic cloth deformation and wrinkles for NFL player jerseys in Madden NFL 21. To our knowledge, this is the first neural cloth simulation featured in a shipped game.

Contributors: Christopher Lewin, James Cobb, James Power

Session: Q&A – Real-Time Rendering 

Date: Wednesday, 11 August 2021

Time: 12pm - 12:30pm PDT

See more at siggraph.org

 

Direct Delta Mush Skinning Compression With Continuous Examples

Technical paper by SEED’s Binh Huy Le and Keven Villeneuve

This paper converts a Direct Delta Mush skinning model to a new model with faster performance and less memory storage by minimizing the approximation error over continuous ranges of motions.

Contributors: Binh Huy Le, Keven Villeneuve, Carlos Gonzalez-Ochoa

Session: Summary and Q&A – Deformation 

Date: Tuesday, 10 August 2021

Time: 10am - 11am PDT

See more at siggraph.org 

Global Illumination Based on Surfels

Course presentation by SEED’s Henrik Halén

Global Illumination Based on Surfels (GIBS) is a solution for calculating indirect diffuse illumination in real-time. This talk will detail the GIBS algorithm and how surfels are used to enable real-time ray-traced global illumination. 

Contributors: Henrik Halen, Andreas Brinck, Kyle Hayward, Xiangshun Bei

Session: Advances in Real-Time Rendering in Games: Part II

Date: Tuesday, 10 August 2021

Time: 9 am - 12 pm PDT

See more at siggraph.org 

Related News

Improving Generalization in Game Agents with Imitation Learning

SEED
Jul 16, 2024
How do we efficiently train in-game AI agents to handle new situations that they haven’t been trained on?

Towards Optimal Training Distribution for Photo-to-Face Models

SEED
Jul 8, 2024
How do we best construct game avatars from photos? This presentation discusses a work in progress with an optimized view of the training data.

Incorporating ML Research Into Audio Production: ExFlowSions Case Study

SEED
Jun 25, 2024
Mónica Villanueva and Jorge García present the challenges and lessons learned from turning a machine learning generative model from a research project into a game production tool.